Loading libraries
rm(list = ls())
library(MASS)
library(tidyverse)
library(haven)
library(readxl)
library(xml2)
library(rvest)
library(janitor)
library(DataExplorer)
library(countrycode)
library(explore)
library(lme4)
library(lmerTest)
library(broom.mixed)
library(ggplot2)
library(dplyr)
library(scales)
library(tidyr)
library(kableExtra)
library(gmodels)
library(flexplot)
library(corrplot)
library(DescTools)
library(caret)
library(ROSE)
library(randomForest)
library(pROC)
library(mice)
library(glmnet)
library(fastDummies)Loading data
Survey data
data_raw <- read_dta("ZA7575.dta")Country-level data sets
This is for joins:
# building a df with country names and codes for the EU-28
codelist <- countrycode::codelist |>
select(country.name.en, iso.name.en, un.name.en, cow.name, ecb, eurostat, iso2c, iso3c, eu28) |>
filter(!is.na(eu28)) GDP per capita, PPP (constant 2021 international $)
Retrieved from the World Bank (https://data.worldbank.org/indicator/NY.GDP.PCAP.PP.KD) for the year 2019.
gdp_data <- read_csv("gdp_pc_ppp_2021.csv", skip = 4, show_col_types = FALSE)## New names:
## • `` -> `...69`head(gdp_data)## # A tibble: 6 × 69
## `Country Name` `Country Code` `Indicator Name` `Indicator Code` `1960` `1961`
## <chr> <chr> <chr> <chr> <lgl> <lgl>
## 1 Aruba ABW GDP per capita,… NY.GDP.PCAP.PP.… NA NA
## 2 Africa Eastern… AFE GDP per capita,… NY.GDP.PCAP.PP.… NA NA
## 3 Afghanistan AFG GDP per capita,… NY.GDP.PCAP.PP.… NA NA
## 4 Africa Western… AFW GDP per capita,… NY.GDP.PCAP.PP.… NA NA
## 5 Angola AGO GDP per capita,… NY.GDP.PCAP.PP.… NA NA
## 6 Albania ALB GDP per capita,… NY.GDP.PCAP.PP.… NA NA
## # ℹ 63 more variables: `1962` <lgl>, `1963` <lgl>, `1964` <lgl>, `1965` <lgl>,
## # `1966` <lgl>, `1967` <lgl>, `1968` <lgl>, `1969` <lgl>, `1970` <lgl>,
## # `1971` <lgl>, `1972` <lgl>, `1973` <lgl>, `1974` <lgl>, `1975` <lgl>,
## # `1976` <lgl>, `1977` <lgl>, `1978` <lgl>, `1979` <lgl>, `1980` <lgl>,
## # `1981` <lgl>, `1982` <lgl>, `1983` <lgl>, `1984` <lgl>, `1985` <lgl>,
## # `1986` <lgl>, `1987` <lgl>, `1988` <lgl>, `1989` <lgl>, `1990` <dbl>,
## # `1991` <dbl>, `1992` <dbl>, `1993` <dbl>, `1994` <dbl>, `1995` <dbl>, …gdp_data <- gdp_data |>
select(`Country Name`, `Country Code`, `2019`)
gdp_data <- gdp_data |>
rename(country_name = `Country Name`,
country_code = `Country Code`,
gdp_pc_ppp = `2019`)
gdp_data <- gdp_data |>
inner_join(select(codelist, iso3c), by = c("country_code" = "iso3c"))
str(gdp_data)## tibble [28 × 3] (S3: tbl_df/tbl/data.frame)
## $ country_name: chr [1:28] "Austria" "Belgium" "Bulgaria" "Cyprus" ...
## $ country_code: chr [1:28] "AUT" "BEL" "BGR" "CYP" ...
## $ gdp_pc_ppp : num [1:28] 64630 60452 27673 46157 47720 ...We now have 28 observations including the UK.
Rural population
Retrieved from the World Bank (https://data.worldbank.org/indicator/SP.RUR.TOTL.ZS).
Data on the % of population living in rural areas over total population.
rural_data <- read_xls("rural_pop.xls", sheet = 1, range = "A4:BL270")
head(rural_data)## # A tibble: 6 × 64
## `Country Name` `Country Code` `Indicator Name` `Indicator Code` `1960` `1961`
## <chr> <chr> <chr> <chr> <dbl> <dbl>
## 1 Aruba ABW Rural populatio… SP.RUR.TOTL.ZS 49.2 49.2
## 2 Africa Eastern… AFE Rural populatio… SP.RUR.TOTL.ZS 85.4 85.2
## 3 Afghanistan AFG Rural populatio… SP.RUR.TOTL.ZS 91.6 91.3
## 4 Africa Western… AFW Rural populatio… SP.RUR.TOTL.ZS 85.3 84.9
## 5 Angola AGO Rural populatio… SP.RUR.TOTL.ZS 89.6 89.2
## 6 Albania ALB Rural populatio… SP.RUR.TOTL.ZS 69.3 69.1
## # ℹ 58 more variables: `1962` <dbl>, `1963` <dbl>, `1964` <dbl>, `1965` <dbl>,
## # `1966` <dbl>, `1967` <dbl>, `1968` <dbl>, `1969` <dbl>, `1970` <dbl>,
## # `1971` <dbl>, `1972` <dbl>, `1973` <dbl>, `1974` <dbl>, `1975` <dbl>,
## # `1976` <dbl>, `1977` <dbl>, `1978` <dbl>, `1979` <dbl>, `1980` <dbl>,
## # `1981` <dbl>, `1982` <dbl>, `1983` <dbl>, `1984` <dbl>, `1985` <dbl>,
## # `1986` <dbl>, `1987` <dbl>, `1988` <dbl>, `1989` <dbl>, `1990` <dbl>,
## # `1991` <dbl>, `1992` <dbl>, `1993` <dbl>, `1994` <dbl>, `1995` <dbl>, …# selecting only the relevant year
rural_data <- rural_data |>
select(`Country Name`, `Country Code`, `2019`) |>
clean_names() |>
rename("rural_pop_percentage" = "x2019")
rural_data <- rural_data |>
inner_join(select(codelist, iso3c), by = c("country_code" = "iso3c"))
str(rural_data)## tibble [28 × 3] (S3: tbl_df/tbl/data.frame)
## $ country_name : chr [1:28] "Austria" "Belgium" "Bulgaria" "Cyprus" ...
## $ country_code : chr [1:28] "AUT" "BEL" "BGR" "CYP" ...
## $ rural_pop_percentage: num [1:28] 41.48 1.96 24.65 33.2 26.08 ...LGBT rights
Found this LGBT rights index on Our World in Data (https://ourworldindata.org/grapher/lgbt-rights-index) which captures whether LGBT+ people enjoy the same rights as cisgender people combining information on 18 different policies. It includes the legal status of same-sex marriage.
lgbt_rights_index <- read.csv("lgbt-rights-index.csv")
lgbt_rights_index <- lgbt_rights_index |>
filter(Year == 2019) |>
inner_join(select(codelist, iso3c), by = c("Code" = "iso3c")) |>
select(-Year) # all observations are from 2019
str(lgbt_rights_index)## 'data.frame': 28 obs. of 3 variables:
## $ Entity : chr "Austria" "Belgium" "Bulgaria" "Croatia" ...
## $ Code : chr "AUT" "BEL" "BGR" "HRV" ...
## $ LGBT..Policy.Index: num 8.92 10 4.94 6.96 3.95 ...Column names can be renamed:
lgbt_rights_index <- lgbt_rights_index |>
rename(country_name = Entity,
country_code = Code,
lgbt_policy_index = LGBT..Policy.Index) Gender inequality index
Gender Development and Gender Inequality indexes, developed by the United Nations Development. Retrieved from https://hdr.undp.org/data-center/documentation-and-downloads for the year 2019.
gender_index <- read_xlsx("UNDP_gender_indexes.xlsx")
gender_index <- gender_index |>
select(-dimension, -note, -year) |> # empty/useless columns
inner_join(select(codelist, iso3c), by = c("countryIsoCode" = "iso3c"))
gender_index |>
distinct(country) |>
nrow()## [1] 28str(gender_index)## tibble [560 × 7] (S3: tbl_df/tbl/data.frame)
## $ countryIsoCode: chr [1:560] "AUT" "AUT" "AUT" "AUT" ...
## $ country : chr [1:560] "Austria" "Austria" "Austria" "Austria" ...
## $ indexCode : chr [1:560] "GII" "GDI" "GDI" "GDI" ...
## $ index : chr [1:560] "Gender Inequality Index" "Gender Development Index" "Gender Development Index" "Gender Development Index" ...
## $ indicatorCode : chr [1:560] "abr" "eys_f" "eys_m" "gdi" ...
## $ indicator : chr [1:560] "Adolescent Birth Rate (births per 1,000 women ages 15-19)" "Expected Years of Schooling, female (years)" "Expected Years of Schooling, male (years)" "Gender Development Index (value)" ...
## $ value : num [1:560] 5.499 16.451 15.725 0.969 0.053 ...We checked that we have indeed 28 distinct countries in the dataset.
This dataset collects many indicators apart from the indexes values. We are selecting only the Gender Development and Gender Inequality indexes (GDI and GII):
gender_index <- gender_index |>
filter(indicatorCode %in% c("gdi", "gii")) |>
select(-c(indexCode, indicatorCode, indicator)) |> # removing redundant columns
pivot_wider(names_from = index, values_from = value)
colnames(gender_index) <- janitor::make_clean_names(colnames(gender_index)) # cleaning spaces and upper casesAnd then exploring them to see which one is a better fit for modeling and predictions:
summary(gender_index$gender_inequality_index)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.0160 0.0555 0.0890 0.1067 0.1335 0.2390summary(gender_index$gender_development_index)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.9560 0.9725 0.9855 0.9856 0.9918 1.0230sd(gender_index$gender_inequality_index)## [1] 0.06664423sd(gender_index$gender_development_index)## [1] 0.0167627We observe that the second one (Gender Development Index) has a very small range, indicating that most countries have nearly identical scores. This is supported by the standard deviation, which shows that the GII is more spread out than the GDI. Being almost constant, GDI won’t add much value to the analysis. This is likely due to the fact that these indexes are created by the United Nations Development Programme for all countries, so it may not capture the finer differences between EU countries.
cor(gender_index$gender_inequality_index,
gender_index$gender_development_index,
use = "complete.obs")## [1] 0.1750589Surprisingly, the two indexes have a very weak positive correlation. While they are not inverse, we interpreted them as measuring opposite things, and had expected a negative correlation. Maybe the correlation coefficient is not useful here because of the low variation of both variables (specially GDI), so ultimately we chose to keep GII and discard GDI.
gender_index <- gender_index |>
select(-gender_development_index)Economist’s Democracy Index
democracy_index <- read_xlsx("EIU_democracy_index.xlsx", sheet = 4)
# the ISO codes were lowercase which impedes the join
democracy_index$geo <- toupper(democracy_index$geo)
# filter for 2019 and EU28 countries
democracy_index <- democracy_index |>
filter(time == 2019) |>
inner_join((select(codelist, iso3c)), by = c("geo" = "iso3c"))
# clean var names
names(democracy_index) <- names(democracy_index) %>%
janitor::make_clean_names() %>%
gsub("_eiu$", "", .)
democracy_index <- democracy_index |>
rename(country_code = geo,
country_name = name,
year = time)
str(democracy_index)## tibble [28 × 10] (S3: tbl_df/tbl/data.frame)
## $ country_code : chr [1:28] "AUT" "BEL" "BGR" "HRV" ...
## $ country_name : chr [1:28] "Austria" "Belgium" "Bulgaria" "Croatia" ...
## $ year : num [1:28] 2019 2019 2019 2019 2019 ...
## $ democracy_index : num [1:28] 82.9 76.4 70.3 65.7 75.9 76.9 92.2 79 92.5 81.2 ...
## $ electoral_pluralism_index : num [1:28] 95.8 95.8 91.7 91.7 91.7 95.8 100 95.8 100 95.8 ...
## $ government_index : num [1:28] 78.6 82.1 64.3 60.7 64.3 67.9 92.9 78.6 89.3 78.6 ...
## $ political_participation_index: num [1:28] 83.3 50 72.2 55.6 66.7 66.7 83.3 66.7 88.9 77.8 ...
## $ political_culture_index : num [1:28] 68.8 68.8 43.8 50 68.8 68.8 93.8 68.8 87.5 68.8 ...
## $ civil_liberties_index : num [1:28] 88.2 85.3 79.4 70.6 88.2 85.3 91.2 85.3 97.1 85.3 ...
## $ change_in_democracy_index : num [1:28] 0 -1.4 0 0 0 ...In this case, we are only keeping the overall index value.
democracy_index <- democracy_index |>
select(country_name, country_code, democracy_index)Joining all country-level data together
country_level_data <- codelist |>
select(iso3c, iso2c) |>
left_join(gdp_data, by = c("iso3c" = "country_code")) |>
# left_join(rural_data, by = c("iso3c" = "country_code")) |> rural population data will probably be discarded
left_join(gender_index, by = c("iso3c" = "country_iso_code")) |>
left_join(lgbt_rights_index, by = c("iso3c" = "country_code")) |>
left_join(democracy_index, by = c("iso3c" = "country_code")) |>
select(-contains("country_")) # removing all duplicated country_name columns that were joined from each data frame
str(country_level_data)## tibble [28 × 7] (S3: tbl_df/tbl/data.frame)
## $ iso3c : chr [1:28] "AUT" "BEL" "BGR" "HRV" ...
## $ iso2c : chr [1:28] "AT" "BE" "BG" "HR" ...
## $ gdp_pc_ppp : num [1:28] 64630 60452 27673 35094 46157 ...
## $ country : chr [1:28] "Austria" "Belgium" "Bulgaria" "Croatia" ...
## $ gender_inequality_index: num [1:28] 0.053 0.048 0.205 0.119 0.235 0.124 0.016 0.092 0.031 0.086 ...
## $ lgbt_policy_index : num [1:28] 8.92 10 4.94 6.96 3.95 ...
## $ democracy_index : num [1:28] 82.9 76.4 70.3 65.7 75.9 76.9 92.2 79 92.5 81.2 ...Data cleaning
Selecting relevant variables in the survey data
We are discarding all variables that relate to trade and
globalization as deemed not relevant for our analysis qa.
We are also discarding variables related to energy policies
qb.
We have also not considered questions specifically about Roma ex
qc8 and qc14 and qc16
Some of the doubts we had:
AGE
x_df <- data_raw |> summarise(mean = mean(qc19), .by = d11)
ggplot(x_df, aes(x = d11, y = mean)) + geom_point()
As relationship seems pretty linear we are going to use the continuous variable for age and there seems to be a clear group (1to4) which is the same used in the variable with 3 categories left, center and right so we will use the 3-categories variable
POLITICAL OPINIONS
x_df <- data_raw |> summarise(mean = mean(qc19), .by = d1)
ggplot(x_df, aes(x = d1, y = mean)) + geom_point() + xlim(1,10)## Warning: Removed 2 rows containing missing values or values outside the scale range
## (`geom_point()`).
For political opinions it seems that the relationship is less linear so we will work on the 5 categories cod
MARRIAGE
x_df <- data_raw |> summarise(mean = mean(qc19), .by = d7r1)
ggplot(x_df, aes(x = d7r1, y = mean)) + geom_point() + xlim(1,5)## Warning: Removed 2 rows containing missing values or values outside the scale range
## (`geom_point()`).
Of all the possible combinations this one seems the best to highlight differences in our target variable
NATIONALITY
There is no easy way to create an immigrant dummy by checking whether
someone does not have the nationality of the country in which he is
being interviewed for the survey. So we are just going to use
q1_29 as a dummy for whether someone owns a non-EU
nationality
POLITICAL INTEREST
Using only polintr as a summary of the whole
d71 question about how strong is your interest in politics
in various domains
EXPERIENCED DISCRIMINATION
For the questions about whether you have experienced discrimination
qc2_ I am keeping only qc2_15 which is a
binary on whether you have experienced any discrimination or not and I
am not keeping the other categories that allowed us to understand if you
had experienced discrimination on the basis of a particular motive. We
can probably assume that if a person is a part of a specific minority
(info from sd2) and is being discriminated is because of
being part of that minority (at least in most cases), therefore it felt
like information we already had (and which we can easily put in our
regression using interaction effects)
PERCIEVED DISCRIMINATION in country
This is a question (qc1) about how widespread you
perceived discrimination is in your country. It is a rather peculiar
question because it asks individUals for perception at the country
level. I think it might be more useful (by aggregating results by
country) to use it to build a country level indicator of perceived
discrimination against certain minorities that are of our interest
rather than use it as an individual level variable. So I will keep them
out of the dataset for now
For the same reason I am also discarding qc4 that asks
whether in your country you feel like candidates with certain
characteristics would be at a disadvantage in the recruitment process.
It still basically asks about perceived discrimination at the country
level.
And the same reasoning also applies to qc7 which asks if
efforts towards reducing discrimination are effective in your
country.
HOW DISCRIMINATORY ARE YOU score
I use qc12 and qc13 to build a score from 1
to 10 of how discriminatory are you against certain minorities. I am
building the score for each minority and then we can decide later if
some are irrelevant.
Note for some categories this score is a bit stupid (ex. voting for whether you would feel uncomfortable if your child was in a love relationship with a old person would give you a high racist score against old people, this is an example of some of the categories for which it is worth excluding the index)
We can also further aggregate to obtain just one score (or obtain religious/ethnic score etc.).
Option also to discard them all (anti lgbtqi sentiment is also
captured in the next index built from qc15)
qc6 also asks about discriminatory behaviors, but is
about elected public official, it does not ask about a situation that
impacts you personally. It also uses different categories for minorities
therefore I prefer to use qc12 and qc13 rather
than qc6
SUPPORTIVE OF LGBTQ RIGHTS INDEX
Using qc15 we can again build an index for how
supportive of lgbtq rights a person is.
I again choose to take the mean across the different answers but we could also use median/mode if we think is better
If we feel each or some answers are particularly useful (given they are closely related with our target variable) we can also use them separately
We could also use qc18 to try to capture anti lgbtq
sentiment, but I preferred qc15 as it seemed more
straightforward (I therfore deleted qc18, but we can put it
back if useful)
MY VOICE COUNTS
I guess that people that feel alienated from society and politics
might be less likely to support lgbtq rights so I took the mean of
d72 question which asked whether you felt like your voice
mattered
OTHERS
qc11 is a strange question feels useless to me, I
removed it for now but we can think about it
I also removed qc9 as I don’t really know what to do
with it and qc17
data <- data_raw |>
select(serialid, # unique identifier
isocntry, # 2 digit country code
d11, # age variables
q1_29, # nationality of interviewee. options given: EU28+Other+DK, using only other = outside of EU
d70, #life satisfaction
polintr, # political interest index (summarizes d71 questions)
starts_with("sd1"), # friends that are minority groups
starts_with("sd2"), # are you part of a minority
sd3, # religion
qc2_15, # experienced discrimination yourself
qc3, # where discrimination took place
starts_with("qc5"), # actions against discrimination
qc10, # how would you report discrimination
starts_with("qc12"), # feelings about colleagues being minority
starts_with("qc13"), # feelings about kid being in a relationship with minority
starts_with("qc15"), # opinions about lgbtqi
qc19, # target variable transgender
qc20, # non-binary genders in documents
d1r1, # political ideology
d7r1, # marital status
d10, # gender binary
d8, # eduaction
d15a_r2, # current occupation (discarded previous occupation d15b)
d25, # rural vs urban
d43t, # phones availiabilty
d60, # financial stress (paying bills)
netuse, # internet index
d63, # social class
starts_with("d72"), # my voice counts
)
paradata <- data_raw |>
select(serialid, # to match it with the other data
p2, p3, p3r, p4, p5, # paradata)
)Removing some of the previously selected variables
sd2_7 to sd2_10: these are possible answer
deemed irrelevant to the question about yourself being part of the
following minorities: sd2_7 other minorities (I don’t know
what other relevant minorities could be there), sd2_8 not
part of minorities (can be deducted from the rest), sd2_9
refusal to respond, sd2_10 DK answers sd2t
summary binary variable for being part of any minority (we are going to
keep the more specific one)
I also remove qc12_nr as I prefer to work on the full
variable instead of the recoded version with less categories. Same for
qc13 and qc18
data <- data |>
# Keep in mind that sd2t does not have NAs so we might want to use that instead of the more specific ones
select(-c(sd2_7, sd2_8, sd2_9, sd2_10, sd2t)) |>
select(-(starts_with("qc12") & ends_with("r"))) |>
select(-(starts_with("qc13") & ends_with("r"))) |>
select(-(starts_with("qc18") & ends_with("r")))Check overall data quality
explore_tbl(data)
plot_intro(data)
All columns are numeric columns, the only one which is not is
isocntry
data |>
select(where(~ !is.numeric(.)))## # A tibble: 27,438 × 1
## isocntry
## <chr>
## 1 BE
## 2 BE
## 3 BE
## 4 BE
## 5 BE
## 6 BE
## 7 BE
## 8 BE
## 9 BE
## 10 BE
## # ℹ 27,428 more rowsMost columns do not have explicit NAs
plot_missing(data)
names(which(colSums(is.na(data)) > 0))## [1] "qc3"Exploiting the fact that the .dta files has attributes (labels) for all its columns.
If we search for attr(colname, "label") you get back the
original long name of the variable
If we instead search for attr(colname, "labels") you get
back all the possible encoding levels of the variable (ex.1,2,3,4 etc.)
and by doing names(attr(colname, "labels")) you get back
the actual meaning of those numbers (ex. 1 = “Yes”, 2 = “No”, etc.)
# Extracting all the full names of the columns
variable_names <- tibble(
var_code = names(data),
var_full_name = sapply(data, function(col) attr(col, "label")))
variable_names## # A tibble: 75 × 2
## var_code var_full_name
## <chr> <chr>
## 1 serialid SERIAL CASE ID (PROVIDED BY KANTAR)
## 2 isocntry COUNTRY CODE - ISO 3166
## 3 d11 AGE EXACT
## 4 q1_29 NATIONALITY: OTHER COUNTRIES
## 5 d70 LIFE SATISFACTION
## 6 polintr POLITICAL INTEREST INDEX (D71 SUMMARIZED)
## 7 sd1_1 CONTACT: PEOPLE OF DIFFERENT ETHNIC ORIGIN
## 8 sd1_2 CONTACT: PEOPLE OF DIFFERENT SKIN COLOUR
## 9 sd1_3 CONTACT: ROMA
## 10 sd1_4 CONTACT: GAY LESBIAN OR BISEXUAL
## # ℹ 65 more rowsThese long names df might be useful to rename the variables systematically all together. Remember in case we filter out variables after this code chunk and in case we use this df to rename variables that there might be disalignments.
Will now look into the labels for the different levels that our factor variables can take:
attr(data$d70, "labels")## Very satisfied Fairly satisfied Not very satisfied
## 1 2 3
## Not at all satisfied DK
## 4 5names(attr(data$d70, "labels"))## [1] "Very satisfied" "Fairly satisfied" "Not very satisfied"
## [4] "Not at all satisfied" "DK"tibble(name_labels = names(attr(data$d70, "labels")),
labels = attr(data$d70, "labels"))## # A tibble: 5 × 2
## name_labels labels
## <chr> <dbl>
## 1 Very satisfied 1
## 2 Fairly satisfied 2
## 3 Not very satisfied 3
## 4 Not at all satisfied 4
## 5 DK 5# Create a list of tibbles containing the labels and their associated name for each variable
list_label_tibbles <-
#Applies a function across all columns of a df and returns results as a list
lapply(names(data), function(col_name) {
labels <- attr(data[[col_name]], "labels") # Extract labels
name_labels <- names(labels) # Extract label names
# Create tibble with the extracted data only if labels exist
if (!is.null(labels)) {
tibble(name_labels = name_labels, labels = labels)}
else {NULL} # Returns a NULL element for columns without labels
})
# Giving to each element of the list as name the name of the variable
list_label_tibbles <- setNames(list_label_tibbles, names(data))
# For example
list_label_tibbles$d70## # A tibble: 5 × 2
## name_labels labels
## <chr> <dbl>
## 1 Very satisfied 1
## 2 Fairly satisfied 2
## 3 Not very satisfied 3
## 4 Not at all satisfied 4
## 5 DK 5Right column is what appears in our data (as a number). Left column is the label that we must assign to that number when we factorize
Cleaning
Initial cleaning and pre-processing
# Recoding together Germany East and West because we are running analysis at the country level
unique(data$isocntry)## [1] "BE" "DK" "GR" "ES" "FI" "FR" "IE" "IT" "LU" "NL"
## [11] "AT" "PT" "SE" "DE-W" "DE-E" "GB" "BG" "CY" "CZ" "EE"
## [21] "HU" "LV" "LT" "MT" "PL" "RO" "SK" "SI" "HR"data <- data |>
mutate(isocntry = case_when(
isocntry %in% c("DE-W", "DE-E") ~ "DE",
TRUE ~ isocntry))
# We might want to join the full name of the countries using the codelist dfSeparating variables for which I can use the attribute labels to factorize them and the variables for which this strategy cannot be used
data <- data |>
rename(friends_trans = sd1_7)
non_factor_variables <- c("serialid", "tnscntry", "isocntry", "d11", "q1_29",
names(data)[startsWith(names(data), "sd1_")],
names(data)[startsWith(names(data), "sd2_")],
names(data)[startsWith(names(data), "qc5_")],
names(data)[startsWith(names(data), "qc12_")],
names(data)[startsWith(names(data), "qc13_")],
names(data)[startsWith(names(data), "qc15_")],
names(data)[startsWith(names(data), "d72_")],
"d8", "opls")
factor_variables <- setdiff(names(data), non_factor_variables)Correctly encoding the factor variables that do not need any further cleaning
# Converting them to factors and assign them their labels automatically
data <- data |>
mutate(across(all_of(factor_variables), labelled::to_factor))
# Turning DK into NAs for all the factor variables
data <- data |>
mutate(across(all_of(factor_variables), ~ fct_na_level_to_value(., extra_levels = "DK")))
# Converting to numeric the variables that should be numeric
# They are already numeric but they carry with them some labels as well that only confuse us, by doing this I remove the labels
data <- data |>
mutate(age = as.numeric(d11),
years_edu = as.numeric(d8)) |>
# Recoding correctly d8 education variable according to unique(data_raw$d11))
mutate(years_edu = case_when(
years_edu %in% c(0, 99) ~ NA, # Refusal and DK as NAs
years_edu == 97 ~ 0, # No full time education = 0
years_edu == 98 ~ age, # still studying = age
TRUE ~ years_edu)) |>
select(-c(d11, d8))
# Converting q1_29 to factor without assigning labels (1 if non-Eu nationality, 0 if EU nationality)
# Same for sd2_
data <- data |>
mutate(nonEU_national = as.factor(q1_29),
across(starts_with("sd2_"), ~ as.factor(.x))) |>
select(-q1_29)Dealing with the other variables on which we do some further pre-processing (feature engineering)
# Creating a variable that counts the number of different minority groups a person has acquaintances with
data <- data |>
mutate(across(starts_with("sd1"), ~ if_else(.x == 1, 1, 0))) |>
mutate(n_friends_minorities = sd1_1+sd1_2+sd1_3+sd1_4+sd1_5+sd1_6+sd1_8) |>
relocate(n_friends_minorities, .before="sd1_1") |>
select(-starts_with("sd1"))
# Creating a variable that counts the number of actions against discrimination that you have taken in the last year
data <- data |>
mutate(across(starts_with("qc5"), ~ if_else(.x == 1, 1, 0))) |>
mutate(n_actions_against_discri = qc5_1+qc5_2+qc5_3+qc5_4) |>
relocate(n_actions_against_discri, .after="qc3") |>
select(-starts_with("qc5"))# Building a discriminatory score
data <- data |>
# Coding as NAs "it depends" and "DK"
mutate(across(starts_with("qc12"), ~ if_else(.x >= 12, NA, .x))) |>
mutate(across(starts_with("qc13"), ~ if_else(.x >= 12, NA, .x))) |>
# Coding as 5 responses = indifferent
mutate(across(starts_with("qc12"), ~ if_else(.x == 11, 5, .x))) |>
mutate(across(starts_with("qc13"), ~ if_else(.x == 11, 5, .x))) |>
# Modifying such that higher is more discriminatory
mutate(roma_discri = 11 - rowMeans(cbind(qc12_1, qc13_1), na.rm = TRUE),
black_discri = 11 - rowMeans(cbind(qc12_2, qc13_2), na.rm = TRUE),
asian_discri = 11 - rowMeans(cbind(qc12_3, qc13_3), na.rm = TRUE),
white_discri = 11 - rowMeans(cbind(qc12_4, qc13_4), na.rm = TRUE),
jewish_discri = 11 - rowMeans(cbind(qc12_5, qc13_5), na.rm = TRUE),
muslim_discri = 11 - rowMeans(cbind(qc12_6, qc13_6), na.rm = TRUE),
buddihst_discri = 11 - rowMeans(cbind(qc12_7, qc13_7), na.rm = TRUE),
christian_discri = 11 - rowMeans(cbind(qc12_8, qc13_8), na.rm = TRUE),
atheist_discri = 11 - rowMeans(cbind(qc12_9, qc13_9), na.rm = TRUE),
lgb_discri = 11 - rowMeans(cbind(qc12_10, qc13_10), na.rm = TRUE),
trans_discri = 11 - rowMeans(cbind(qc12_11, qc13_11), na.rm = TRUE),
intersex_discri = 11 - rowMeans(cbind(qc12_12, qc13_12), na.rm = TRUE),
disability_discri = 11 - rowMeans(cbind(qc12_13, qc13_13), na.rm = TRUE),
young_discri = 11 - rowMeans(cbind(qc12_14, qc13_14), na.rm = TRUE),
old_discri = 11 - rowMeans(cbind(qc12_15, qc13_15), na.rm = TRUE)) |>
select(-starts_with("qc12")) |>
select(-starts_with("qc13"))
# I am deleting the discrimination index against young and old people
# This is because one of the question is: how comfortable you would feel if one of your children was in a love relationship with a person from group x.
# It is totally acceptable that people would not feel comfortable with their kid dating an old person without that accounting for being discriminatory against old people
data <- data |>
select(-c("old_discri", "young_discri"))# Supportive of lbtq rights index
data <- data |>
mutate(across(starts_with("qc15"), ~ if_else(.x == 5, NA, .x))) |>
# Scale of 1 to 4, 1 = supportive, 4 = homophobic
mutate(antilgbtq_rights = round(rowMeans(cbind(qc15_1, qc15_2, qc15_3), na.rm = TRUE), 2)) |>
select(-starts_with("qc15"))# My voice counts index
data <- data |>
mutate(across(starts_with("d72"), ~ if_else(.x > 4, NA, .x))) |>
mutate(social_alienation = rowMeans(cbind(d72_1, d72_2), na.rm = TRUE)) |>
select(-starts_with("d72"))
# The higher the more people think their voice does not matterThis should be our final selection of variables.
We still need to rename them appropriately and check that all the NAs are correctly encoded by looking at the summary.
Rename columns appropriately and move them around to order the dataframe
data <- data |>
rename(
country = isocntry,
life_sat = d70,
ethnic_minority = sd2_1,
skincolor_minority = sd2_2,
religious_minority = sd2_3,
roma_minority = sd2_4,
sexual_minority = sd2_5,
disability_minority = sd2_6,
religion = sd3,
disc = qc2_15,
disc_where = qc3,
disc_contact = qc10,
trans_docs = qc19,
gender_docs = qc20,
left_right = d1r1,
marital_status = d7r1,
gender = d10,
occupation = d15a_r2,
community = d25,
phone_access = d43t,
bill_issues = d60,
internet_use = netuse,
social_class = d63
) Now, we will transform the variable disc, which was originally coded in a negative way (1 = “Not mentioned”, 2 = “No, you haven’t been discriminated against”), into a positive dummy variable to make its interpretation more straightforward. The variable is 1 if a person has been subject to discrimination
data <- data |>
mutate(suffered_discr = as.factor(ifelse(disc == "Not mentioned", 1, 0))) |>
select(-disc) |>
relocate(suffered_discr, .before = disc_where)# Relocating to have a ordered df
data <- data |>
relocate(c("age", "gender", "years_edu","community", "marital_status", "occupation", "social_class", "religion", "nonEU_national", "phone_access", "bill_issues", "internet_use"), .after = country) |>
relocate(c("left_right", "social_alienation"), .after = polintr) |>
relocate(c("friends_trans", "n_friends_minorities", "n_actions_against_discri"), .after = gender_docs)
# Assigning labels to columns which have a difficult meaning
attr(data$gender, "label") <- NULL
attr(data$nonEU_national, "label") <- "OWNS A NON-EU NATIONALITY"
attr(data$social_alienation, "label") <- "HIGHER -> THINK THEIR VOICE DOESN'T MATTER"
attr(data$ethnic_minority, "label") <- "ARE YOU PART OF X MINORITY"
attr(data$skincolor_minority, "label") <- "ARE YOU PART OF X MINORITY"
attr(data$religious_minority, "label") <- "ARE YOU PART OF X MINORITY"
attr(data$roma_minority, "label") <- "ARE YOU PART OF X MINORITY"
attr(data$sexual_minority, "label") <- "ARE YOU PART OF X MINORITY"
attr(data$disability_minority, "label") <- "ARE YOU PART OF X MINORITY"
attr(data$disability_minority, "label") <- "ARE YOU PART OF X MINORITY"
attr(data$disability_minority, "label") <- "ARE YOU PART OF X MINORITY"
attr(data$suffered_discr, "label") <- "HAVE YOU BEEN SUBJECT TO DISCRIMINATION"
attr(data$n_friends_minorities, "label") <- "YOU KNOW PEOPLE FROM # NUMBER OF DIFFERENT MINORITES"
attr(data$n_actions_against_discri, "label") <- "YOU HAVE DONE # NUMBER OF DIFFERENT ACTIONS TO FIGHT DISCRIMINATIONS"
attr(data$roma_discri, "label") <- "HOW DISCRIMINATORY ARE YOU AGAINST X"
attr(data$black_discri, "label") <- "HOW DISCRIMINATORY ARE YOU AGAINST X"
attr(data$asian_discri, "label") <- "HOW DISCRIMINATORY ARE YOU AGAINST X"
attr(data$white_discri, "label") <- "HOW DISCRIMINATORY ARE YOU AGAINST X"
attr(data$jewish_discri, "label") <- "HOW DISCRIMINATORY ARE YOU AGAINST X"
attr(data$muslim_discri, "label") <- "HOW DISCRIMINATORY ARE YOU AGAINST X"
attr(data$buddihst_discri, "label") <- "HOW DISCRIMINATORY ARE YOU AGAINST X"
attr(data$christian_discri, "label") <- "HOW DISCRIMINATORY ARE YOU AGAINST X"
attr(data$atheist_discri, "label") <- "HOW DISCRIMINATORY ARE YOU AGAINST X"
attr(data$atheist_discri, "label") <- "HOW DISCRIMINATORY ARE YOU AGAINST X"
attr(data$lgb_discri, "label") <- "HOW DISCRIMINATORY ARE YOU AGAINST X"
attr(data$trans_discri, "label") <- "HOW DISCRIMINATORY ARE YOU AGAINST X"
attr(data$intersex_discri, "label") <- "HOW DISCRIMINATORY ARE YOU AGAINST X"
attr(data$disability_discri, "label") <- "HOW DISCRIMINATORY ARE YOU AGAINST X"
attr(data$antilgbtq_rights, "label") <- "HIGHER -> THEY OPPOSE MORE RIGHTS TO LGBTQ"summary(data)## serialid country age gender
## Min. : 1 Length:27438 Min. :15.00 Man :12492
## 1st Qu.: 6860 Class :character 1st Qu.:37.00 Woman:14946
## Median :13720 Mode :character Median :53.00
## Mean :13720 Mean :51.56
## 3rd Qu.:20579 3rd Qu.:66.00
## Max. :27438 Max. :98.00
##
## years_edu community
## Min. : 0.00 Rural area or village : 8776
## 1st Qu.:17.00 Small or middle sized town:10767
## Median :18.00 Large town : 7881
## Mean :19.66 NA's : 14
## 3rd Qu.:22.00
## Max. :90.00
## NA's :387
## marital_status
## (Re-)Married (1-4 in d7) :14673
## Single living with partner (5-8 in d7): 3321
## Single (9-10 in d7) : 4314
## Divorced or separated (11-12 in d7) : 2243
## Widow (13-14 in d7) : 2712
## Other (SPONT.) : 107
## Refusal (SPONT.) : 68
## occupation
## Retired (4 in d15a) :8791
## Manual workers (15 to 18 in d15a) :5883
## Other white collars (13 or 14 in d15a):3536
## Managers (10 to 12 in d15a) :2911
## Self-employed (5 to 9 in d15a) :1979
## Students (2 in d15a) :1676
## (Other) :2662
## social_class religion
## The middle class of society :13068 Catholic :11198
## The working class of society : 7233 Orthodox Christian : 4016
## The lower middle class of society: 4070 Non believer or agnostic: 3694
## The upper middle class of society: 1889 Protestant : 3031
## None (SPONTANEOUS) : 229 Atheist : 2109
## (Other) : 389 (Other) : 3220
## NA's : 560 NA's : 170
## nonEU_national phone_access bill_issues
## 0:27316 Mobile only :14555 Most of the time : 2054
## 1: 122 Landline only : 802 From time to time : 6538
## Landline & mobile:11576 Almost never/never:18467
## No telephone : 505 Refusal (SPONT.) : 379
##
##
##
## internet_use life_sat
## Everyday/Almost everyday :19900 Very satisfied : 7242
## Two or three times a week : 1701 Fairly satisfied :15356
## About once a week : 434 Not very satisfied : 3736
## Two or three times a month: 164 Not at all satisfied: 1002
## Less often : 350 NA's : 102
## Never/No access : 4311
## No Internet access at all : 578
## polintr left_right social_alienation ethnic_minority
## Strong : 4644 (1 - 4) Left :7082 Min. :1.000 0:26603
## Medium :13701 (5 - 6) Centre:9313 1st Qu.:1.500 1: 835
## Low : 4387 (7 -10) Right :6354 Median :2.000
## Not at all: 4706 DK/Refusal :4689 Mean :2.329
## 3rd Qu.:3.000
## Max. :4.000
## NA's :1000
## skincolor_minority religious_minority roma_minority sexual_minority
## 0:26923 0:26416 0:27001 0:27006
## 1: 515 1: 1022 1: 437 1: 432
##
##
##
##
##
## disability_minority suffered_discr
## 0:26756 0:23150
## 1: 682 1: 4288
##
##
##
##
##
## disc_where
## In a public space : 893
## At work : 788
## When looking for a job : 642
## At a café, restaurant, bar or nightclub : 322
## By healthcare personnel (e.g. a receptionist, nurse or doctor): 308
## (Other) : 1054
## NA's :23431
## disc_contact
## The police :8769
## A friend or family member :5386
## An equalities body or ombudsman (SPECIFY THE NAME ACCORDING TO THE COUNTRY):3795
## A lawyer :2329
## Courts :1225
## (Other) :3601
## NA's :2333
## trans_docs gender_docs friends_trans n_friends_minorities
## Yes :14463 Yes :10856 Yes : 2644 Min. :0.000
## No : 9695 No :13395 No :23520 1st Qu.:1.000
## NA's: 3280 NA's: 3187 Refusal (SPONTANEOUS): 306 Median :3.000
## NA's : 968 Mean :3.029
## 3rd Qu.:5.000
## Max. :7.000
##
## n_actions_against_discri roma_discri black_discri asian_discri
## Min. :0.0000 Min. : 1.000 Min. : 1.000 Min. : 1.000
## 1st Qu.:0.0000 1st Qu.: 1.500 1st Qu.: 1.000 1st Qu.: 1.000
## Median :0.0000 Median : 4.500 Median : 3.000 Median : 2.500
## Mean :0.3855 Mean : 4.631 Mean : 3.579 Mean : 3.387
## 3rd Qu.:0.0000 3rd Qu.: 7.000 3rd Qu.: 5.500 3rd Qu.: 5.500
## Max. :4.0000 Max. :10.000 Max. :10.000 Max. :10.000
## NA's :757 NA's :542 NA's :592
## white_discri jewish_discri muslim_discri buddihst_discri
## Min. : 1.000 Min. : 1.00 Min. : 1.000 Min. : 1.000
## 1st Qu.: 1.000 1st Qu.: 1.00 1st Qu.: 1.000 1st Qu.: 1.000
## Median : 1.000 Median : 2.00 Median : 4.000 Median : 3.000
## Mean : 1.785 Mean : 3.18 Mean : 4.363 Mean : 3.576
## 3rd Qu.: 2.000 3rd Qu.: 5.00 3rd Qu.: 6.500 3rd Qu.: 5.500
## Max. :10.000 Max. :10.00 Max. :10.000 Max. :10.000
## NA's :403 NA's :603 NA's :662 NA's :761
## christian_discri atheist_discri lgb_discri trans_discri
## Min. : 1.000 Min. : 1.000 Min. : 1.000 Min. : 1.000
## 1st Qu.: 1.000 1st Qu.: 1.000 1st Qu.: 1.000 1st Qu.: 2.000
## Median : 1.000 Median : 1.500 Median : 4.000 Median : 5.000
## Mean : 1.904 Mean : 2.802 Mean : 4.399 Mean : 4.934
## 3rd Qu.: 2.000 3rd Qu.: 4.000 3rd Qu.: 6.500 3rd Qu.: 7.500
## Max. :10.000 Max. :10.000 Max. :10.000 Max. :10.000
## NA's :414 NA's :517 NA's :536 NA's :1081
## intersex_discri disability_discri antilgbtq_rights
## Min. : 1.000 Min. : 1.000 Min. :1.000
## 1st Qu.: 1.500 1st Qu.: 1.000 1st Qu.:1.000
## Median : 5.000 Median : 2.500 Median :2.000
## Mean : 4.825 Mean : 2.977 Mean :2.147
## 3rd Qu.: 7.500 3rd Qu.: 4.500 3rd Qu.:3.000
## Max. :10.000 Max. :10.000 Max. :4.000
## NA's :1331 NA's :585 NA's :791Our dataset seems quite balanced across the different countries
data |> count(country)## # A tibble: 28 × 2
## country n
## <chr> <int>
## 1 AT 1027
## 2 BE 1028
## 3 BG 1032
## 4 CY 503
## 5 CZ 1008
## 6 DE 1537
## 7 DK 1004
## 8 EE 1003
## 9 ES 1005
## 10 FI 1003
## # ℹ 18 more rowsAlthough some levels of occupation have more observations than
others, we have enough observations for each level so we do not need to
aggregate over different levels for the variable
occupation
data |> count(occupation)## # A tibble: 8 × 2
## occupation n
## <fct> <int>
## 1 Self-employed (5 to 9 in d15a) 1979
## 2 Managers (10 to 12 in d15a) 2911
## 3 Other white collars (13 or 14 in d15a) 3536
## 4 Manual workers (15 to 18 in d15a) 5883
## 5 House persons (1 in d15a) 1358
## 6 Unemployed (3 in d15a) 1304
## 7 Retired (4 in d15a) 8791
## 8 Students (2 in d15a) 1676Very few people declare themselves to be the higher class of society, nonetheless we keep this level because it makes sense
data |> count(social_class)## # A tibble: 9 × 2
## social_class n
## <fct> <int>
## 1 The working class of society 7233
## 2 The lower middle class of society 4070
## 3 The middle class of society 13068
## 4 The upper middle class of society 1889
## 5 The higher class of society 157
## 6 Other (SPONTANEOUS) 59
## 7 None (SPONTANEOUS) 229
## 8 Refusal (SPONTANEOUS) 173
## 9 <NA> 560Given the low number of observations in some categories of the
variable religion and the high number of categories we opt
to aggregate some of them, otherwise we risk too much noise in our
models.
data |> count(religion)## # A tibble: 16 × 2
## religion n
## <fct> <int>
## 1 Catholic 11198
## 2 Orthodox Christian 4016
## 3 Protestant 3031
## 4 Other Christian 1183
## 5 Jewish 58
## 6 Muslim - Shia 77
## 7 Muslim - Sunni 178
## 8 Other Muslim 137
## 9 Sikh 13
## 10 Buddhist 58
## 11 Hindu 32
## 12 Atheist 2109
## 13 Non believer or agnostic 3694
## 14 Other 1171
## 15 Refusal (SPONTANEOUS) 313
## 16 <NA> 170# Checking if the means of groups we are going to aggregate are similar
data |>
mutate(trans_docs=as.numeric(trans_docs)) |>
summarise(mean = mean(trans_docs, na.rm=TRUE), .by = religion) |>
arrange(mean)## # A tibble: 16 × 2
## religion mean
## <fct> <dbl>
## 1 Sikh 1.25
## 2 Atheist 1.27
## 3 Non believer or agnostic 1.28
## 4 Protestant 1.30
## 5 Buddhist 1.33
## 6 Other 1.37
## 7 Jewish 1.38
## 8 Other Christian 1.43
## 9 Catholic 1.43
## 10 Hindu 1.44
## 11 Muslim - Shia 1.45
## 12 <NA> 1.45
## 13 Other Muslim 1.49
## 14 Refusal (SPONTANEOUS) 1.49
## 15 Muslim - Sunni 1.54
## 16 Orthodox Christian 1.58# We are going to group together atheist with agnostic
# We are also going to put sikh, buddhists, jewish and hindu into the other category
# Finally we are going to group together all muslims
data <- data |>
mutate(religion = fct_collapse(religion,
"Non-believers" = c("Atheist", "Non believer or agnostic"),
"Other" = c("Sikh", "Buddhist", "Jewish", "Hindu", "Other"),
"Muslim" = c("Muslim - Shia", "Muslim - Sunni", "Other Muslim")))
#This is what we end up with
data |> count(religion)## # A tibble: 9 × 2
## religion n
## <fct> <int>
## 1 Catholic 11198
## 2 Orthodox Christian 4016
## 3 Protestant 3031
## 4 Other Christian 1183
## 5 Other 1332
## 6 Muslim 392
## 7 Non-believers 5803
## 8 Refusal (SPONTANEOUS) 313
## 9 <NA> 170Recoding missing values
Now we will substitute de “Refusal” answers in the remaining variables as NAs. If the respondent refuses to answer it’s equivalent to not knowing his or her answer. We exclude friends_trans because that category could be worth analyzing.
factor_variables <- names(data)[sapply(data, is.factor)]
data <- data %>%
mutate(across(
all_of(setdiff(factor_variables, "friends_trans")), # Exclude "friends_trans"
~ {
# Look for levels that contain "REFUSAL"
refusal_levels <- grep("REFUSAL", levels(.), value = TRUE, ignore.case = TRUE)
# If there are levels containing "REFUSAL"
if (length(refusal_levels) > 0) {
# Convert in NA
fct_recode(., NULL = refusal_levels)
}
# if not remain without changes
else {
.
}
}
))
# Mutate NONE level of social class to NA
data <- data %>%
mutate(social_class = fct_recode(social_class, NULL = "None (SPONTANEOUS)"))
# We turn marital_status level OTHER into NAs, as it is difficult to give it any other meaning. Same for social class
data <- data %>%
mutate(marital_status = fct_recode(marital_status, NULL = "Other (SPONT.)"),
social_class = fct_recode(social_class, NULL = "Other (SPONTANEOUS)")) plot_intro(data)
plot_missing(data)
The total number of missing observations is quite low (4%) so missing data should not be a huge problem
Given the high percentage of missing values we delete
disc_where. This variable was expected to have a high
percentage of missingness as it is a question that applies only to
people that have been subject to discrimination.
The variable with the second highest number of missing data is
left_right, given the importance of this variable it is
probably worth to impute those values.
Next there are the variables trans_docs and
gender_docs which are respectively our target variable and
a closely related variable
Then there is disc_contact which will be deleted as
well, given that it does not add meaningful information to our
analysis
data <- data |>
select(-c("disc_where", "disc_contact"))Not using paradata for now. We can discuss how to use it
Exploratory Data Analysis
Plotting the distribution of the numeric variables
library(e1071)
# Identify numeric variables
numeric_vars <- names(data)[sapply(data, is.numeric)]
# Creating histogramas y calculating skweness
for (var in numeric_vars) {
p <- ggplot(data, aes(x = .data[[var]])) +
geom_histogram(binwidth = 1, fill = "blue", color = "black") +
labs(title = paste("Histogram of", var), x = var, y = "Count") +
theme_minimal()
print(p)
skew <- skewness(data[[var]], na.rm = TRUE)
cat("Skewness of", var, ":", skew, "\n")
# Suggest transformation if skeness is high
if (abs(skew) > 1) {
cat("--> Consider applying a logarithmic transformation to", var, "\n")
}
}
## Skewness of serialid : 0
## Skewness of age : -0.1189211## Warning: Removed 387 rows containing non-finite outside the scale range
## (`stat_bin()`).
## Skewness of years_edu : 2.379305
## --> Consider applying a logarithmic transformation to years_edu## Warning: Removed 1000 rows containing non-finite outside the scale range
## (`stat_bin()`).
## Skewness of social_alienation : 0.2702432
## Skewness of n_friends_minorities : -0.04656275
## Skewness of n_actions_against_discri : 2.466341
## --> Consider applying a logarithmic transformation to n_actions_against_discri## Warning: Removed 757 rows containing non-finite outside the scale range
## (`stat_bin()`).
## Skewness of roma_discri : 0.3302414## Warning: Removed 542 rows containing non-finite outside the scale range
## (`stat_bin()`).
## Skewness of black_discri : 0.8274431## Warning: Removed 592 rows containing non-finite outside the scale range
## (`stat_bin()`).
## Skewness of asian_discri : 0.9145309## Warning: Removed 403 rows containing non-finite outside the scale range
## (`stat_bin()`).
## Skewness of white_discri : 2.363763
## --> Consider applying a logarithmic transformation to white_discri## Warning: Removed 603 rows containing non-finite outside the scale range
## (`stat_bin()`).
## Skewness of jewish_discri : 1.047646
## --> Consider applying a logarithmic transformation to jewish_discri## Warning: Removed 662 rows containing non-finite outside the scale range
## (`stat_bin()`).
## Skewness of muslim_discri : 0.4638859## Warning: Removed 761 rows containing non-finite outside the scale range
## (`stat_bin()`).
## Skewness of buddihst_discri : 0.8297239## Warning: Removed 414 rows containing non-finite outside the scale range
## (`stat_bin()`).
## Skewness of christian_discri : 2.142768
## --> Consider applying a logarithmic transformation to christian_discri## Warning: Removed 517 rows containing non-finite outside the scale range
## (`stat_bin()`).
## Skewness of atheist_discri : 1.316445
## --> Consider applying a logarithmic transformation to atheist_discri## Warning: Removed 536 rows containing non-finite outside the scale range
## (`stat_bin()`).
## Skewness of lgb_discri : 0.441202## Warning: Removed 1081 rows containing non-finite outside the scale range
## (`stat_bin()`).
## Skewness of trans_discri : 0.2225545## Warning: Removed 1331 rows containing non-finite outside the scale range
## (`stat_bin()`).
## Skewness of intersex_discri : 0.2687168## Warning: Removed 585 rows containing non-finite outside the scale range
## (`stat_bin()`).
## Skewness of disability_discri : 1.054419
## --> Consider applying a logarithmic transformation to disability_discri## Warning: Removed 791 rows containing non-finite outside the scale range
## (`stat_bin()`).
## Skewness of antilgbtq_rights : 0.4429458Analysis of individual-level variables
We must keep in mind our Target variable is qc19 “Do you think that transgender persons should be able to change their civil documents to match their inner gender identity?”
data_percent <- data |>
group_by(trans_docs) |>
summarise(count = n()) |>
mutate(percentage = count / sum(count) * 100)
ggplot(data_percent, aes(x = trans_docs, y = percentage, fill = trans_docs)) +
geom_bar(stat = "identity") +
geom_text(aes(label = sprintf("%.1f%%", percentage)),
vjust = -0.5, size = 4, color = "black") +
scale_y_continuous(labels = scales::percent_format(scale = 1)) +
labs(
title = "Overall distribution of support for trans people to change \ntheir gender in civil documents",
x = "Support for Transgender Rights",
y = "Percentage"
) +
theme_minimal() +
theme(legend.position = "none")
Taking a look to our variable of interest alone, we see how the 52.7% of our sample are in favor of trans people to change their gender in their civil documents. However, there is also a significant opposition (35,3%), and a 12% who answered “Don’t know”. We will try to explore this distribution along the variables we consider to be most important for our analysis.
–> When we turned DK into NAs for all the factor variables, we also changed it for qc19 (now trans_docs). We should keep throughout our analysis in mind that NAs for qc19 are actually DK. Later we can code it as DK instead of NAs to have better graphs.
Sociodemographic variables
Gender
data_summary <- data |>
count(trans_docs, gender, name = "n") |>
group_by(gender) |>
mutate(percentage = n / sum(n))
ggplot(data_summary, aes(x = trans_docs, y = percentage, fill = gender)) +
geom_bar(stat = "identity", position = "dodge") +
geom_text(aes(label = scales::percent(percentage, accuracy = 1)),
position = position_dodge(width = 0.9), vjust = -0.2, size = 4) +
scale_y_continuous(labels = percent_format()) +
labs(
title = "Distribution of support by gender",
x = "Support for trans people changing their civil documents",
y = "Percentage within Gender",
fill = "Gender"
) +
theme_minimal()
# Crear una tabla de contingencia
contingency_table <- table(data$gender, data$trans_docs)
# Realizar la prueba de chi-cuadrado
chisq_test <- chisq.test(contingency_table)
print(chisq_test)##
## Pearson's Chi-squared test with Yates' continuity correction
##
## data: contingency_table
## X-squared = 92.715, df = 1, p-value < 2.2e-16Men exhibit a lower percentage of favorable or dk responses and a higher rate of rejection compared to women. There is a statistically significant association between gender and our target variable, being women more supportive
Age
data |>
mutate(age_bin = cut(age, breaks = seq(min(age, na.rm = TRUE), max(age, na.rm = TRUE), by = 10), include.lowest = TRUE)) |>
drop_na(age_bin) |> # There are 4 observations above 95 y.o. that do not fall within any of the previously difined bins. Given their low number we drop them
count(age_bin, trans_docs) |>
group_by(age_bin) |>
mutate(percentage = n / sum(n) * 100) |> # Compute percentages
ggplot(aes(x = age_bin, y = percentage, fill = trans_docs)) +
geom_bar(stat = "identity", position = "stack") +
coord_flip() + # Horizontal bars
labs(x = "Age Bins", y = "Percentage", fill = "Trans Docs",
title = "Stacked Horizontal Bar Plot of Trans Docs by Age Group") +
theme_minimal()
Younger people seem more likely to support the right for transgender people to have their gender changed on official documents.
We also notice a big increase of NAs for older people, meaning older people are less likely to respond to this question (because of unfamiliarity with the topic maybe)
So how would that distribution look if we get rid of NAs
data |>
drop_na(trans_docs) |>
mutate(age_bin = cut(age, breaks = seq(min(age, na.rm = TRUE), max(age, na.rm = TRUE), by = 10), include.lowest = TRUE)) |>
drop_na(age_bin) |> # There are 4 observations above 95 y.o. that do not fall within any of the previously difined bins. Given their low number we drop them
count(age_bin, trans_docs) |>
group_by(age_bin) |>
mutate(percentage = n / sum(n) * 100) |> # Compute percentages
ggplot(aes(x = age_bin, y = percentage, fill = trans_docs)) +
geom_bar(stat = "identity", position = "stack") +
coord_flip() + # Horizontal bars
labs(x = "Age Bins", y = "Percentage", fill = "Trans Docs",
title = "Stacked Horizontal Bar Plot of Trans Docs by Age Group") +
theme_minimal()
We see that differences among age groups are not so evident anymore.
sum(is.na(data$age))## [1] 0Religiosity
We have two variables related to religiosity: religion (the religious affiliation professed by the respondent) and religious_minority (whether or not the respondent belongs to a religious minority group).
For the first one it’s better to show a cross table instead of a plot, since there are a lot of categories
CrossTable(data$religion, data$trans_docs,
digits = 2,
expected = FALSE,
asresid = TRUE,
chisq = TRUE,
prop.chisq = FALSE,
format = "SPSS")##
## Cell Contents
## |-------------------------|
## | Count |
## | Row Percent |
## | Column Percent |
## | Total Percent |
## | Adj Std Resid |
## |-------------------------|
##
## Total Observations in Table: 23792
##
## | data$trans_docs
## data$religion | Yes | No | Row Total |
## -------------------|-----------|-----------|-----------|
## Catholic | 5605 | 4241 | 9846 |
## | 56.93% | 43.07% | 41.38% |
## | 39.27% | 44.55% | |
## | 23.56% | 17.83% | |
## | -8.09 | 8.09 | |
## -------------------|-----------|-----------|-----------|
## Orthodox Christian | 1421 | 1959 | 3380 |
## | 42.04% | 57.96% | 14.21% |
## | 9.96% | 20.58% | |
## | 5.97% | 8.23% | |
## | -22.99 | 22.99 | |
## -------------------|-----------|-----------|-----------|
## Protestant | 1866 | 807 | 2673 |
## | 69.81% | 30.19% | 11.23% |
## | 13.07% | 8.48% | |
## | 7.84% | 3.39% | |
## | 11.00 | -11.00 | |
## -------------------|-----------|-----------|-----------|
## Other Christian | 597 | 449 | 1046 |
## | 57.07% | 42.93% | 4.40% |
## | 4.18% | 4.72% | |
## | 2.51% | 1.89% | |
## | -1.97 | 1.97 | |
## -------------------|-----------|-----------|-----------|
## Other | 764 | 446 | 1210 |
## | 63.14% | 36.86% | 5.09% |
## | 5.35% | 4.68% | |
## | 3.21% | 1.87% | |
## | 2.30 | -2.30 | |
## -------------------|-----------|-----------|-----------|
## Muslim | 159 | 160 | 319 |
## | 49.84% | 50.16% | 1.34% |
## | 1.11% | 1.68% | |
## | 0.67% | 0.67% | |
## | -3.72 | 3.72 | |
## -------------------|-----------|-----------|-----------|
## Non-believers | 3860 | 1458 | 5318 |
## | 72.58% | 27.42% | 22.35% |
## | 27.05% | 15.32% | |
## | 16.22% | 6.13% | |
## | 21.28 | -21.28 | |
## -------------------|-----------|-----------|-----------|
## Column Total | 14272 | 9520 | 23792 |
## | 59.99% | 40.01% | |
## -------------------|-----------|-----------|-----------|
##
##
## Statistics for All Table Factors
##
##
## Pearson's Chi-squared test
## ------------------------------------------------------------
## Chi^2 = 973.2956 d.f. = 6 p = 5.330102e-207
##
##
##
## Minimum expected frequency: 127.6429Out of all observations Catholic, non-believers, Orthodox Christians and Protestants sum up to the 81.04% of our sample, being the rest underrepresented.
data_summary <- data |>
count(trans_docs, religious_minority, name = "n") |>
group_by(religious_minority) |>
mutate(percentage = n / sum(n))
ggplot(data_summary, aes(x = trans_docs, y = percentage, fill = religious_minority)) +
geom_bar(stat = "identity", position = "dodge") +
geom_text(aes(label = scales::percent(percentage, accuracy = 1)),
position = position_dodge(width = 0.9), vjust = -0.2, size = 4) +
scale_y_continuous(labels = percent_format()) +
labs(
title = "Distribution of support by religious minority",
x = "Support for trans people changing their civil documents",
y = "Percentage within religious_minority",
fill = "religious_minority"
) +
theme_minimal()
Ideology
data_summary <- data |>
count(trans_docs, left_right, name = "n") |>
group_by(left_right) |>
mutate(percentage = n / sum(n))
ggplot(data_summary, aes(x = trans_docs, y = percentage, fill = left_right)) +
geom_bar(stat = "identity", position = "dodge") +
geom_text(aes(label = scales::percent(percentage, accuracy = 1)),
position = position_dodge(width = 0.9), vjust = -0.2, size = 4) +
scale_y_continuous(labels = percent_format()) +
labs(
title = "Distribution of support by ideology",
x = "Support for trans people changing their civil documents",
y = "Percentage within ideology",
fill = "ideology"
) +
theme_minimal()
Stronger left-wing support for trans rights. Right-wing respondents are the most divided, with high opposition levels. Non-responses are highest among those without ideological alignment.
Education
ggplot(data, aes(x = trans_docs, y = years_edu)) +
geom_violin() +
labs(x = "Support for trans people changing their civil documents", y = "Age when stopped full-time education") +
ggtitle("Distribution of support by education")## Warning: Removed 387 rows containing non-finite outside the scale range
## (`stat_ydensity()`).
Support doesn’t seem to be related to education.
Area of residence
data_summary <- data |>
count(trans_docs, community, name = "n") |>
group_by(community) |>
mutate(percentage = n / sum(n))
ggplot(data_summary, aes(x = trans_docs, y = percentage, fill = community)) +
geom_bar(stat = "identity", position = "dodge") +
geom_text(aes(label = scales::percent(percentage, accuracy = 1)),
position = position_dodge(width = 0.9), vjust = -0.2, size = 4) +
scale_y_continuous(labels = percent_format()) +
labs(
title = "Distribution of support by area of residence",
x = "Support for trans people changing their civil documents",
y = "Percentage within area of residence",
fill = "area of residence"
) +
theme_minimal()
Support does not vary much by area of residence.
Other individual-level variables
Having trans friends
data_summary <- data |>
count(trans_docs, friends_trans, name = "n") |>
group_by(friends_trans) |>
mutate(percentage = n / sum(n))
ggplot(data_summary, aes(x = trans_docs, y = percentage, fill = friends_trans)) +
geom_bar(stat = "identity", position = "dodge") +
geom_text(aes(label = scales::percent(percentage, accuracy = 1)),
position = position_dodge(width = 0.9), vjust = -0.2, size = 4) +
scale_y_continuous(labels = percent_format()) +
labs(
title = "Distribution of support by haivng trans friends",
x = "Support for trans people changing their civil documents",
y = "Percentage within groups",
fill = "Has Trans Friends"
) +
theme_minimal()
Having trans friends is associated with a higher support, while those who refuse to disclose their connections to trans people tend to oppose more.
Country-level EDA
Replication of the plot in Marga’s document. This is probably not needed in the final version of the document.
country_support <- data %>%
mutate(
trans_docs = case_when(
is.na(trans_docs) ~ "DK",
trans_docs == "Yes" ~ "1",
trans_docs == "No" ~ "2",
TRUE ~ as.character(trans_docs)
)
) %>%
group_by(country, trans_docs = trans_docs) %>%
summarise(count = n(), .groups = "drop") %>%
group_by(country) %>%
mutate(proportion = (count / sum(count))*100) %>%
ungroup()
ggplot(country_support, aes(x = factor(country, levels = country_support %>%
filter(trans_docs == "1") %>%
arrange(desc(proportion)) %>%
pull(country)),
y = proportion,
fill = factor(trans_docs, levels = c("1", "2", "DK")))) +
geom_bar(stat = "identity", position = position_stack(reverse = TRUE)) +
scale_fill_manual(values = c("1" = "#497ba9", "2" = "#d56e6e", "DK" = "#9a9595"),
name = "",
labels = c("Yes", "No", "Don't know")) +
geom_text(aes(label = round(proportion)),
position = position_stack(reverse = TRUE, vjust = 0.5),
size = 3.5, color = "white") +
labs(
title = "QC9: Do you think transgender persons should be able to change their civil documents to match their inner gender identity?",
x = "",
y = ""
) +
theme_minimal() +
theme(axis.text.x = element_text(angle = 45, hjust = 1),
axis.text.y = element_blank(),
axis.ticks.y = element_blank(),
plot.title = element_text(size = 9),
panel.grid.major.y = element_blank(),
legend.position = "bottom")
There are some mismatches, I guess the data might have become distorted at some point during processing, but I don’t know when.
trans_docs_prop <- country_support %>%
filter(trans_docs == "1") %>%
select(country, proportion) %>%
rename(trans_support = proportion)
country_long <- country_level_data %>%
inner_join(trans_docs_prop, by = c("iso2c" = "country")) |>
pivot_longer(cols = c(gdp_pc_ppp, gender_inequality_index, lgbt_policy_index, democracy_index),
names_to = "variable", values_to = "value")
ggplot(country_long, aes(x = value, y = trans_support)) +
geom_smooth(method = "lm", se = FALSE, color = "lightgray") + # we can remove this
geom_point(size = 2, color = "blue", alpha = 0.7) +
geom_text(aes(label = iso3c), vjust = -0.5, hjust = 0.5, size = 3) +
facet_wrap(~variable, scales = "free_x") +
labs(
title = "Relationship between country-level variables and trans support",
x = "Country-level variable",
y = "Proportion of Yes answers"
) +
theme_minimal()## `geom_smooth()` using formula = 'y ~ x'
Democracy and LGBT Policy indeces seem to have a positive linear relationship with the target variable, while Gender Inequality index has a negative linear relationship. The relationship with GDP per capita is non-linear (logarithmic?). There appears to be a “ceiling” of support, beyond which increases in GDP per capita lose effect.
Boxplots for country-level variables:
ggplot(country_long, aes(y = value, x = variable)) +
geom_boxplot(outlier.color = "red", outlier.shape = 16, fill = "lightblue") +
coord_flip() +
theme_minimal() +
labs(title = "Distribution of country-level variables", x = NULL, y = "value") +
facet_wrap(~variable, scales = "free") +
theme(axis.text.y = element_blank(),
axis.ticks.x = element_blank())
country_level_data_cor <- country_level_data %>%
inner_join(trans_docs_prop, by = c("iso2c" = "country"))
cor_matrix <- cor(country_level_data_cor %>%
select(gdp_pc_ppp, democracy_index, gender_inequality_index,
lgbt_policy_index, trans_support),
use = "complete.obs")
corrplot(cor_matrix, method = "color", type = "upper",
addCoef.col = "black", tl.col = "black",
col = colorRampPalette(c("blue", "white", "red"))(200))
Some heavy correlations which is a little worrying, but as we are going to use these data to build cross-level interactions, this should not compromise the reliability of our analysis too much.
Paradata
# Extracting labels in paradata
list_label_tibbles_paradata <- lapply(names(paradata), function(col_name) {
labels <- attr(paradata[[col_name]], "labels")
name_labels <- names(labels)
if (!is.null(labels)) {
tibble(name_labels = name_labels, labels = labels)
} else {
NULL
}
})
# Asign names to list elements
list_label_tibbles_paradata <- setNames(list_label_tibbles_paradata, names(paradata))
# Convert into factor
paradata <- paradata %>%
mutate(across(where(~ !is.null(attr(., "labels"))), labelled::to_factor))
# Merging datasets for the analysis
merged_paradata <- merge(data, paradata, by = "serialid", all.x = TRUE)Number of persons present during interview:
library(gmodels)
# Convert NA in a explicit category
merged_paradata$trans_docs <- as.character(merged_paradata$trans_docs)
merged_paradata$trans_docs[is.na(merged_paradata$trans_docs)] <- "DK"
merged_paradata$trans_docs <- as.factor(merged_paradata$trans_docs)
# CrossTable
CrossTable(merged_paradata$p4, merged_paradata$trans_docs,
digits=2,
expected=F,
asresid=T,
chisq=TRUE,
prop.chisq=F,
format="SPSS")##
## Cell Contents
## |-------------------------|
## | Count |
## | Row Percent |
## | Column Percent |
## | Total Percent |
## | Adj Std Resid |
## |-------------------------|
##
## Total Observations in Table: 27438
##
## | merged_paradata$trans_docs
## merged_paradata$p4 | DK | No | Yes | Row Total |
## ---------------------------------|-----------|-----------|-----------|-----------|
## Two (interviewer and respondent) | 2806 | 8146 | 12428 | 23380 |
## | 12.00% | 34.84% | 53.16% | 85.21% |
## | 85.55% | 84.02% | 85.93% | |
## | 10.23% | 29.69% | 45.29% | |
## | 0.58 | -4.10 | 3.54 | |
## ---------------------------------|-----------|-----------|-----------|-----------|
## Three | 428 | 1316 | 1758 | 3502 |
## | 12.22% | 37.58% | 50.20% | 12.76% |
## | 13.05% | 13.57% | 12.16% | |
## | 1.56% | 4.80% | 6.41% | |
## | 0.52 | 2.97 | -3.19 | |
## ---------------------------------|-----------|-----------|-----------|-----------|
## Four | 36 | 189 | 218 | 443 |
## | 8.13% | 42.66% | 49.21% | 1.61% |
## | 1.10% | 1.95% | 1.51% | |
## | 0.13% | 0.69% | 0.79% | |
## | -2.50 | 3.25 | -1.49 | |
## ---------------------------------|-----------|-----------|-----------|-----------|
## Five or more | 10 | 44 | 59 | 113 |
## | 8.85% | 38.94% | 52.21% | 0.41% |
## | 0.30% | 0.45% | 0.41% | |
## | 0.04% | 0.16% | 0.22% | |
## | -1.02 | 0.80 | -0.11 | |
## ---------------------------------|-----------|-----------|-----------|-----------|
## Column Total | 3280 | 9695 | 14463 | 27438 |
## | 11.95% | 35.33% | 52.71% | |
## ---------------------------------|-----------|-----------|-----------|-----------|
##
##
## Statistics for All Table Factors
##
##
## Pearson's Chi-squared test
## ------------------------------------------------------------
## Chi^2 = 26.44717 d.f. = 6 p = 0.0001837381
##
##
##
## Minimum expected frequency: 13.50827The table shows a significant association between the number of people present during the interview and support for transgender people to change their documents
Regarding the duration of the interview we have 2 options p3 and p3r. We will use p3r to have a simpler analysis
# CrossTable
CrossTable(merged_paradata$p3r, merged_paradata$trans_docs,
digits=2,
expected=F,
asresid=T,
chisq=TRUE,
prop.chisq=F,
format="SPSS")##
## Cell Contents
## |-------------------------|
## | Count |
## | Row Percent |
## | Column Percent |
## | Total Percent |
## | Adj Std Resid |
## |-------------------------|
##
## Total Observations in Table: 27438
##
## | merged_paradata$trans_docs
## merged_paradata$p3r | DK | No | Yes | Row Total |
## --------------------|-----------|-----------|-----------|-----------|
## Up to 14 minutes | 73 | 224 | 260 | 557 |
## | 13.11% | 40.22% | 46.68% | 2.03% |
## | 2.23% | 2.31% | 1.80% | |
## | 0.27% | 0.82% | 0.95% | |
## | 0.85 | 2.43 | -2.88 | |
## --------------------|-----------|-----------|-----------|-----------|
## 15 - 29 minutes | 782 | 2284 | 3456 | 6522 |
## | 11.99% | 35.02% | 52.99% | 23.77% |
## | 23.84% | 23.56% | 23.90% | |
## | 2.85% | 8.32% | 12.60% | |
## | 0.10 | -0.61 | 0.52 | |
## --------------------|-----------|-----------|-----------|-----------|
## 30 - 44 minutes | 1429 | 4388 | 6305 | 12122 |
## | 11.79% | 36.20% | 52.01% | 44.18% |
## | 43.57% | 45.26% | 43.59% | |
## | 5.21% | 15.99% | 22.98% | |
## | -0.75 | 2.66 | -2.06 | |
## --------------------|-----------|-----------|-----------|-----------|
## 45 - 59 minutes | 703 | 1993 | 3039 | 5735 |
## | 12.26% | 34.75% | 52.99% | 20.90% |
## | 21.43% | 20.56% | 21.01% | |
## | 2.56% | 7.26% | 11.08% | |
## | 0.80 | -1.04 | 0.48 | |
## --------------------|-----------|-----------|-----------|-----------|
## 60 - 74 minutes | 202 | 529 | 908 | 1639 |
## | 12.32% | 32.28% | 55.40% | 5.97% |
## | 6.16% | 5.46% | 6.28% | |
## | 0.74% | 1.93% | 3.31% | |
## | 0.48 | -2.67 | 2.25 | |
## --------------------|-----------|-----------|-----------|-----------|
## 75 - 89 minutes | 49 | 123 | 276 | 448 |
## | 10.94% | 27.46% | 61.61% | 1.63% |
## | 1.49% | 1.27% | 1.91% | |
## | 0.18% | 0.45% | 1.01% | |
## | -0.67 | -3.52 | 3.80 | |
## --------------------|-----------|-----------|-----------|-----------|
## 90 minutes and more | 42 | 154 | 219 | 415 |
## | 10.12% | 37.11% | 52.77% | 1.51% |
## | 1.28% | 1.59% | 1.51% | |
## | 0.15% | 0.56% | 0.80% | |
## | -1.16 | 0.76 | 0.02 | |
## --------------------|-----------|-----------|-----------|-----------|
## Column Total | 3280 | 9695 | 14463 | 27438 |
## | 11.95% | 35.33% | 52.71% | |
## --------------------|-----------|-----------|-----------|-----------|
##
##
## Statistics for All Table Factors
##
##
## Pearson's Chi-squared test
## ------------------------------------------------------------
## Chi^2 = 36.84302 d.f. = 12 p = 0.0002368813
##
##
##
## Minimum expected frequency: 49.61003Respondent cooperation
data_summary <- merged_paradata |>
count(p5, trans_docs, name = "n") |>
group_by(p5) |>
mutate(percentage = n / sum(n))
ggplot(data_summary, aes(x = p5, y = percentage, fill = trans_docs)) +
geom_bar(stat = "identity", position = "dodge") +
geom_text(aes(label = scales::percent(percentage, accuracy = 1)),
position = position_dodge(width = 0.9), vjust = -0.2, size = 4) +
scale_y_continuous(labels = percent_format()) +
labs(
title = "Distribution of support by Respondent cooperation",
x = "Respondent cooperation",
y = "Percentage within groups",
fill = "Support"
) +
theme_minimal()
# Calcular porcentajes
plot_data <- merged_paradata %>%
group_by(p5, trans_docs) %>%
summarise(count = n(), .groups = 'drop') %>%
mutate(percentage = count / sum(count) * 100)Respondents who engaged better in the survey were more likely to express support.
Correlation and multicollinearity
Now we want to take a look at the possible multicollinearity of our explanatory variables. For it, we calculate the correlation of our numerical variables. As we have too many variables, we visualize just those with a strong correlation to focus on key dependencies.
cor_matrix <- cor(data %>%
select_if(is.numeric) %>%
select(-serialid),
use = "complete.obs")
corrplot(cor_matrix, method = "color", type = "upper",
tl.col = "black",
col = colorRampPalette(c("blue", "white", "red"))(200))
# Create a matrix where only correlations >= 0.7 are maintained
cor_filtered <- ifelse(abs(cor_matrix) >= 0.7, cor_matrix, NA)
# Graph
corrplot(cor_filtered, method = "color", type = "upper",
tl.col = "black",
col = colorRampPalette(c("blue", "white", "red"))(200),
na.label = " ",
insig = "blank") 
Most strong correlations are among variables related to race, religion or sexual orientation discrimination. Consequently, we are grouping them into 3 new composite variables by averaging related ones, in order to reduce multicollinearity.
# Creating grouped variables
data <- data %>%
mutate(
racial_discri = rowMeans(select(., roma_discri, black_discri, asian_discri), na.rm = TRUE), #no white
sexual_discri = rowMeans(select(., lgb_discri, trans_discri, intersex_discri), na.rm = TRUE),
religious_discri = rowMeans(select(., jewish_discri, muslim_discri, buddihst_discri), na.rm = TRUE)
)
# Removing original variables to avoid redundancy
data <- data |>
select(-c(roma_discri, black_discri, asian_discri, lgb_discri, trans_discri, intersex_discri, jewish_discri, muslim_discri, buddihst_discri))
# Graphical representation
cor_matrix <- cor(data %>%
select_if(is.numeric) %>%
select(-serialid),
use = "complete.obs")
corrplot(cor_matrix, method = "color", type = "upper",
tl.col = "black",
col = colorRampPalette(c("blue", "white", "red"))(200))
We realize our new variables are still highly correlated between them. For reducing the dimensionality of the dataset even more while preserving information we create one single variable for general minority discrimination.
# Creating grouped variable
data <- data %>%
mutate(
minority_discri = rowMeans(select(., racial_discri, sexual_discri, religious_discri, disability_discri), na.rm = TRUE)) We decided to exclude white_discri, atheist_discri, christian_discri because we realized they had a median of 1 and a quite small mean, meaning there is almost no reported discrimination against these groups in the dataset.
summary(data$white_discri)## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## 1.000 1.000 1.000 1.785 2.000 10.000 403summary(data$atheist_discri)## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## 1.000 1.000 1.500 2.802 4.000 10.000 517summary(data$christian_discri)## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## 1.000 1.000 1.000 1.904 2.000 10.000 414data <- data |>
select(-c(white_discri, atheist_discri, christian_discri, racial_discri, sexual_discri, religious_discri, disability_discri))Final check of the correlation matrix to confirm that multicollinearity has been reduced.
cor_matrix <- cor(data %>%
select_if(is.numeric) %>%
select(-serialid),
use = "complete.obs")
corrplot(cor_matrix, method = "color", type = "upper",
addCoef.col = "black", tl.col = "black",
col = colorRampPalette(c("blue", "white", "red"))(200))
Class imbalance
prop.table(table(data$trans_docs, useNA = "ifany"))##
## Yes No <NA>
## 0.5271157 0.3533421 0.1195422prop.table(table(data$trans_docs, useNA = "no"))##
## Yes No
## 0.5986837 0.4013163Our target variable has a 60/40 distribution so we are not worried about class imbalance.
Less represented classes in other variables have already been aggregated if deemed necessary.
Analysis of missing values
Here we analyse the NA reponses to our target variable. This is a sort of robustness check to understand our data and learn if there are patterns in NA response that we should be worried about e.g. if there are specific demographics of people who are less likely to respond.
Overall the analysis below shows that non response is similar to the descriptive data and aligned with some groups reported “No” to supporting trans_docs in c19. So we’re more at risk of underreporting “no” votes in this survey due to non-response. The correlation is low though so it’s not a major concern.
Who is more likely to not respond to our target?
There are 3,280 NA responses to the target variable. To try understand if the missing values are at random, we will test the correlation between NA response and Use the DK (don’t know) for our target variable.
In the descriptive analysis above, we have already seen in raw terms that NA responses were more frequent from some groups e.g.
women,
older people,
people who also responded NA for political ideology,
People who do not have trans friends and those who refused to respond to the friendship question had higher NA responses to the target variable.
People with lower survey cooperation
By country, we already understand from the challenge description that the NA responses vary. This is a significant disparity.
Create a binary variable for the DK
cntry_name <- codelist |> select(iso2c, country_name = country.name.en)
dk_target <- data |>
mutate(target_NA = ifelse(is.na(trans_docs), 1, 0)) |>
left_join(cntry_name, by = join_by(country == iso2c)) |>
dplyr::select(-trans_docs, -serialid, -country)
table(dk_target$target_NA)##
## 0 1
## 24158 3280Confirm DK rates by country. They vary from 1.4% in Belgium to 28.5% in Bulgaria. Overall, the average is 11.95%.
dk_target |>
group_by(country_name) |>
summarise(count_na = sum(target_NA),
num_resp = length(country_name),
pct_na = count_na/num_resp*100) |>
ggplot(aes(x=reorder(country_name, -pct_na), y = pct_na))+
geom_col()+
theme(axis.text.x = element_text(angle = 45, hjust = 1),
axis.title.x = element_blank()) +
scale_y_continuous(labels = scales::percent_format(scale = 1)) +
labs(y = "Proportion of NA responses")
If all NA responses to the target are removed, this is how much the “Yes” count increases for each of our countries. We see this is not proportional. This is a statistical phenomenon. distribution of the variable looks by country. The NA vote removal, makes our differences in Yes/No differences appear larger.
data |>
group_by(country) |>
summarise(yes_count = sum(trans_docs == "Yes", na.rm=TRUE),
num_resp = sum(!is.na(trans_docs)),
num_na = sum(is.na(trans_docs)),
pct_yes_withna = yes_count / length(country)*100,
pct_yes = yes_count/num_resp*100)|>
ggplot(aes(x = reorder(country, -pct_yes))) +
geom_col(aes(y = pct_yes), fill = "red") + # First bar (pct_yes)
geom_col(aes(y = pct_yes_withna), fill = "yellow", alpha = 0.5) + # Second bar (pct_yes_withna)
theme(axis.text.x = element_text(angle = 45, hjust = 1),
axis.title.x = element_blank()) +
scale_y_continuous(labels = scales::percent_format(scale = 1),
limits = c(0,100)) +
labs(title ="Support for transgender rights to legally change documents, with and without NA's")
Check correlation with DK of target
Run model to test what is correlated with DK response, use Cramers V for association between the factor variables and correlation for the numeric variables in the cleaned data.
- Model the data for DK responses against the factor variables.
factor_subset <- dk_target %>%
dplyr::select(target_NA, where(is.factor)) |>
mutate(target_NA = factor(target_NA))
# Run cramers V for factors
target_var <- "target_NA"
factor_variables <- names(factor_subset)
factor_variables <- factor_variables[factor_variables != target_var]
cramers_v_results <- list()
for (variable in factor_variables) {
contingency_table <- table(factor_subset[[target_var]],
factor_subset[[variable]])
cramers_v <- CramerV(contingency_table)
cramers_v_results[[variable]] <- cramers_v
}
# Create a Tibble for Results
cat_results <- tibble(variable = names(cramers_v_results),
cramers_v = unlist(cramers_v_results)) |>
arrange(desc(cramers_v))
cat_results## # A tibble: 22 × 2
## variable cramers_v
## <chr> <dbl>
## 1 internet_use 0.136
## 2 social_class 0.0975
## 3 occupation 0.0852
## 4 marital_status 0.0831
## 5 gender_docs 0.0820
## 6 religion 0.0763
## 7 phone_access 0.0711
## 8 life_sat 0.0642
## 9 polintr 0.0621
## 10 friends_trans 0.0581
## # ℹ 12 more rowsThis shows all of the factors have quite low association with the NA responses. The highest being internet use. This is a good sign that the missing values are random.
- Look at the numeric variables and test correlations:
numeric_subset <- dk_target %>%
dplyr::select(target_NA, where(is.numeric))
target_var <- "target_NA"
numeric_variables <- names(numeric_subset)[names(numeric_subset) != target_var]
cor_results <- list()
for (variable in numeric_variables) {
correlation <- cor(numeric_subset$target_NA,
numeric_subset[[variable]],
use = "pairwise.complete.obs")
cor_results[[variable]] <- correlation
}
# Create a Tibble for Results
cor_results <- tibble(variable = names(cor_results),
cor = unlist(cor_results)) |>
arrange(cor)
cor_results## # A tibble: 7 × 2
## variable cor
## <chr> <dbl>
## 1 n_actions_against_discri -0.0988
## 2 n_friends_minorities -0.0965
## 3 years_edu -0.0544
## 4 social_alienation 0.0566
## 5 minority_discri 0.0635
## 6 age 0.0982
## 7 antilgbtq_rights 0.108Again, this is not too much cause for concern. We only have around 10% correlations, positive and negative with the target variable.
Modelling relationship with key variables and non-response
Here we run a logistic regression to test for the most important/significant variables. First, we make a subset of data with only our variables that were most correlated in the seciton above (use above +/- 9.5% correlation and above 10% cramers V) and also include gender and country.
cor_results |> filter(cor > 0.09 | cor < -0.9) |> pull(variable)## [1] "age" "antilgbtq_rights"cat_results |> filter(cramers_v >0.1) |> pull(variable)## [1] "internet_use"Now model with those variables to see if they are significant in explaining the DK values. Gender will also be included as a key variable.
We run a stepwise AIC on these most correlated variables and then use the best model to test the overall model fit.
# first, run stepwise to determine most important
# run base model
dk_fit_null <- glm(target_NA ~ 1,
data = dk_target,
family = "binomial")
# run full fit model of most correlated vars with country (also age^2 for good practice)
dk_fit <- glm(target_NA ~ gender + age + I(age*age) + antilgbtq_rights + internet_use + social_class + country_name,
data = dk_target,
family = "binomial")
# use stepwise to select best mode l
aic_1 <- MASS::stepAIC(dk_fit, scope = list(upper = dk_fit,
lower = dk_fit_null),
direction = "both", k = 2, trace=0) # forward based on AIC
# filter vars significant at 5% and calculate exponential
broom::tidy(aic_1) |>
filter(p.value<0.05) |>
mutate(oddsratio = exp(estimate)) |>
select(term, oddsratio, p.value)## # A tibble: 29 × 3
## term oddsratio p.value
## <chr> <dbl> <dbl>
## 1 (Intercept) 0.0500 8.78e-40
## 2 genderWoman 1.20 2.01e- 5
## 3 I(age * age) 1.00 4.77e- 4
## 4 antilgbtq_rights 1.13 9.69e- 7
## 5 internet_useTwo or three times a week 1.21 2.72e- 2
## 6 internet_useTwo or three times a month 0.307 4.97e- 3
## 7 internet_useNever/No access 1.28 2.49e- 4
## 8 internet_useNo Internet access at all 1.57 4.62e- 4
## 9 social_classThe lower middle class of society 0.766 4.62e- 5
## 10 social_classThe middle class of society 0.713 4.09e-11
## # ℹ 19 more rowsThe best model is the one without age but includes age^2. So we run the full model to keep the lower level variables included.
The model has some interesting findings to who did not respond to our findings. Some things we can see with the odds ratios (excluding interpretation of countries as that is covered above):
women are around 20% more likely to give NA responses
Anti-lgbti rights people were about 10% more likely to not respond
Internet use was significant but is not interpertable. If you had not used the internet (higher NA likelihood) or used it 2-3 times a week (lower NA likelihood) compared to everyday use
Social class was significant at all levels, compared to the working class, you were more likely to not respond to our target variable if you reported being in the lower middle, middle or upper middle class. I.e. working class were less likely to answer this question.
Below is an option using undersampling which is probably more legit too.
# split to test and training
na_model <- glm(target_NA ~ .,
data = dk_target,
family = "binomial")
summary(na_model)##
## Call:
## glm(formula = target_NA ~ ., family = "binomial", data = dk_target)
##
## Coefficients:
## Estimate Std. Error
## (Intercept) -5.096435 0.505490
## age 0.012178 0.004217
## genderWoman 0.164789 0.082464
## years_edu -0.005912 0.007160
## communitySmall or middle sized town 0.060070 0.095266
## communityLarge town -0.083705 0.106848
## marital_statusSingle living with partner (5-8 in d7) -0.229059 0.153178
## marital_statusSingle (9-10 in d7) -0.151896 0.148656
## marital_statusDivorced or separated (11-12 in d7) 0.289686 0.129040
## marital_statusWidow (13-14 in d7) 0.216811 0.125780
## occupationManagers (10 to 12 in d15a) 0.074469 0.188675
## occupationOther white collars (13 or 14 in d15a) -0.002162 0.186434
## occupationManual workers (15 to 18 in d15a) -0.087856 0.174101
## occupationHouse persons (1 in d15a) -0.244480 0.263347
## occupationUnemployed (3 in d15a) 0.032945 0.250771
## occupationRetired (4 in d15a) -0.152771 0.176731
## occupationStudents (2 in d15a) -0.516985 0.364050
## social_classThe lower middle class of society -0.191067 0.127529
## social_classThe middle class of society -0.102517 0.102911
## social_classThe upper middle class of society -0.048871 0.182548
## social_classThe higher class of society 0.028047 0.527417
## religionOrthodox Christian -0.272443 0.208576
## religionProtestant 0.161109 0.154425
## religionOther Christian -0.132124 0.206172
## religionOther -0.791153 0.279671
## religionMuslim 0.691685 0.325376
## religionNon-believers -0.020914 0.130285
## nonEU_national1 -0.370848 1.018180
## phone_accessLandline only -0.110733 0.229728
## phone_accessLandline & mobile 0.039715 0.100780
## phone_accessNo telephone -0.500657 0.355297
## bill_issuesFrom time to time 0.232590 0.188589
## bill_issuesAlmost never/never 0.457448 0.188085
## internet_useTwo or three times a week 0.184435 0.156891
## internet_useAbout once a week 0.437365 0.257105
## internet_useTwo or three times a month -1.580741 1.011667
## internet_useLess often 0.079182 0.337876
## internet_useNever/No access 0.290840 0.128823
## internet_useNo Internet access at all 0.312489 0.268088
## life_satFairly satisfied 0.053242 0.101376
## life_satNot very satisfied 0.291434 0.144484
## life_satNot at all satisfied 0.005602 0.247800
## polintrMedium 0.080670 0.107402
## polintrLow 0.126350 0.136224
## polintrNot at all -0.045332 0.151273
## left_right(5 - 6) Centre 0.122380 0.097494
## left_right(7 -10) Right 0.094612 0.105449
## social_alienation 0.124139 0.048298
## ethnic_minority1 0.461184 0.233612
## skincolor_minority1 -0.927202 0.522311
## religious_minority1 -0.483626 0.269626
## roma_minority1 -0.234027 0.404566
## sexual_minority1 -0.429264 0.520931
## disability_minority1 0.278993 0.250759
## suffered_discr1 -0.380922 0.137183
## gender_docsNo 0.536267 0.092952
## friends_transNo -0.075223 0.151250
## friends_transRefusal (SPONTANEOUS) 0.147667 0.397164
## n_friends_minorities 0.037060 0.024872
## n_actions_against_discri -0.150414 0.064844
## antilgbtq_rights 0.055886 0.052789
## minority_discri -0.028983 0.022540
## country_nameBelgium -1.057217 0.426007
## country_nameBulgaria 1.258296 0.346358
## country_nameCroatia -0.006931 0.341891
## country_nameCyprus 0.618536 0.449668
## country_nameCzechia 0.063576 0.328735
## country_nameDenmark 0.020749 0.350265
## country_nameEstonia 0.498044 0.333545
## country_nameFinland 0.506632 0.328111
## country_nameFrance 0.209453 0.338444
## country_nameGermany 0.551572 0.302573
## country_nameGreece 0.155828 0.405321
## country_nameHungary -0.199701 0.337837
## country_nameIreland 0.042946 0.348477
## country_nameItaly 0.258879 0.342212
## country_nameLatvia 0.686826 0.320758
## country_nameLithuania 0.118117 0.329320
## country_nameLuxembourg -0.023112 0.449294
## country_nameMalta -0.619311 0.644793
## country_nameNetherlands -0.325966 0.367757
## country_namePoland 0.501405 0.326395
## country_namePortugal -0.339504 0.391052
## country_nameRomania -0.023516 0.400689
## country_nameSlovakia 0.249307 0.319901
## country_nameSlovenia 0.151497 0.338876
## country_nameSpain -0.389991 0.392042
## country_nameSweden 0.821909 0.320433
## country_nameUnited Kingdom 0.544943 0.329095
## z value Pr(>|z|)
## (Intercept) -10.082 < 2e-16 ***
## age 2.888 0.00388 **
## genderWoman 1.998 0.04568 *
## years_edu -0.826 0.40898
## communitySmall or middle sized town 0.631 0.52833
## communityLarge town -0.783 0.43339
## marital_statusSingle living with partner (5-8 in d7) -1.495 0.13481
## marital_statusSingle (9-10 in d7) -1.022 0.30688
## marital_statusDivorced or separated (11-12 in d7) 2.245 0.02477 *
## marital_statusWidow (13-14 in d7) 1.724 0.08476 .
## occupationManagers (10 to 12 in d15a) 0.395 0.69307
## occupationOther white collars (13 or 14 in d15a) -0.012 0.99075
## occupationManual workers (15 to 18 in d15a) -0.505 0.61382
## occupationHouse persons (1 in d15a) -0.928 0.35322
## occupationUnemployed (3 in d15a) 0.131 0.89548
## occupationRetired (4 in d15a) -0.864 0.38736
## occupationStudents (2 in d15a) -1.420 0.15558
## social_classThe lower middle class of society -1.498 0.13407
## social_classThe middle class of society -0.996 0.31917
## social_classThe upper middle class of society -0.268 0.78892
## social_classThe higher class of society 0.053 0.95759
## religionOrthodox Christian -1.306 0.19148
## religionProtestant 1.043 0.29682
## religionOther Christian -0.641 0.52162
## religionOther -2.829 0.00467 **
## religionMuslim 2.126 0.03352 *
## religionNon-believers -0.161 0.87247
## nonEU_national1 -0.364 0.71569
## phone_accessLandline only -0.482 0.62979
## phone_accessLandline & mobile 0.394 0.69353
## phone_accessNo telephone -1.409 0.15880
## bill_issuesFrom time to time 1.233 0.21746
## bill_issuesAlmost never/never 2.432 0.01501 *
## internet_useTwo or three times a week 1.176 0.23977
## internet_useAbout once a week 1.701 0.08892 .
## internet_useTwo or three times a month -1.563 0.11817
## internet_useLess often 0.234 0.81471
## internet_useNever/No access 2.258 0.02397 *
## internet_useNo Internet access at all 1.166 0.24377
## life_satFairly satisfied 0.525 0.59945
## life_satNot very satisfied 2.017 0.04369 *
## life_satNot at all satisfied 0.023 0.98196
## polintrMedium 0.751 0.45259
## polintrLow 0.928 0.35366
## polintrNot at all -0.300 0.76443
## left_right(5 - 6) Centre 1.255 0.20939
## left_right(7 -10) Right 0.897 0.36960
## social_alienation 2.570 0.01016 *
## ethnic_minority1 1.974 0.04837 *
## skincolor_minority1 -1.775 0.07587 .
## religious_minority1 -1.794 0.07286 .
## roma_minority1 -0.578 0.56295
## sexual_minority1 -0.824 0.40992
## disability_minority1 1.113 0.26588
## suffered_discr1 -2.777 0.00549 **
## gender_docsNo 5.769 7.96e-09 ***
## friends_transNo -0.497 0.61895
## friends_transRefusal (SPONTANEOUS) 0.372 0.71004
## n_friends_minorities 1.490 0.13622
## n_actions_against_discri -2.320 0.02036 *
## antilgbtq_rights 1.059 0.28975
## minority_discri -1.286 0.19851
## country_nameBelgium -2.482 0.01308 *
## country_nameBulgaria 3.633 0.00028 ***
## country_nameCroatia -0.020 0.98383
## country_nameCyprus 1.376 0.16896
## country_nameCzechia 0.193 0.84665
## country_nameDenmark 0.059 0.95276
## country_nameEstonia 1.493 0.13539
## country_nameFinland 1.544 0.12257
## country_nameFrance 0.619 0.53600
## country_nameGermany 1.823 0.06831 .
## country_nameGreece 0.384 0.70064
## country_nameHungary -0.591 0.55444
## country_nameIreland 0.123 0.90192
## country_nameItaly 0.756 0.44936
## country_nameLatvia 2.141 0.03225 *
## country_nameLithuania 0.359 0.71984
## country_nameLuxembourg -0.051 0.95898
## country_nameMalta -0.960 0.33681
## country_nameNetherlands -0.886 0.37542
## country_namePoland 1.536 0.12449
## country_namePortugal -0.868 0.38530
## country_nameRomania -0.059 0.95320
## country_nameSlovakia 0.779 0.43579
## country_nameSlovenia 0.447 0.65483
## country_nameSpain -0.995 0.31985
## country_nameSweden 2.565 0.01032 *
## country_nameUnited Kingdom 1.656 0.09775 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 6149.9 on 18337 degrees of freedom
## Residual deviance: 5702.8 on 18249 degrees of freedom
## (9100 observations deleted due to missingness)
## AIC: 5880.8
##
## Number of Fisher Scoring iterations: 7broom::tidy(na_model)## # A tibble: 89 × 5
## term estimate std.error statistic p.value
## <chr> <dbl> <dbl> <dbl> <dbl>
## 1 (Intercept) -5.10 0.505 -10.1 6.62e-24
## 2 age 0.0122 0.00422 2.89 3.88e- 3
## 3 genderWoman 0.165 0.0825 2.00 4.57e- 2
## 4 years_edu -0.00591 0.00716 -0.826 4.09e- 1
## 5 communitySmall or middle sized town 0.0601 0.0953 0.631 5.28e- 1
## 6 communityLarge town -0.0837 0.107 -0.783 4.33e- 1
## 7 marital_statusSingle living with partn… -0.229 0.153 -1.50 1.35e- 1
## 8 marital_statusSingle (9-10 in d7) -0.152 0.149 -1.02 3.07e- 1
## 9 marital_statusDivorced or separated (1… 0.290 0.129 2.24 2.48e- 2
## 10 marital_statusWidow (13-14 in d7) 0.217 0.126 1.72 8.48e- 2
## # ℹ 79 more rowsexp(coefficients(na_model))## (Intercept)
## 0.006118521
## age
## 1.012252085
## genderWoman
## 1.179144394
## years_edu
## 0.994105573
## communitySmall or middle sized town
## 1.061910918
## communityLarge town
## 0.919702513
## marital_statusSingle living with partner (5-8 in d7)
## 0.795281376
## marital_statusSingle (9-10 in d7)
## 0.859077470
## marital_statusDivorced or separated (11-12 in d7)
## 1.336008000
## marital_statusWidow (13-14 in d7)
## 1.242109894
## occupationManagers (10 to 12 in d15a)
## 1.077311509
## occupationOther white collars (13 or 14 in d15a)
## 0.997840105
## occupationManual workers (15 to 18 in d15a)
## 0.915892418
## occupationHouse persons (1 in d15a)
## 0.783111899
## occupationUnemployed (3 in d15a)
## 1.033494121
## occupationRetired (4 in d15a)
## 0.858326624
## occupationStudents (2 in d15a)
## 0.596316021
## social_classThe lower middle class of society
## 0.826076903
## social_classThe middle class of society
## 0.902562665
## social_classThe upper middle class of society
## 0.952304428
## social_classThe higher class of society
## 1.028443714
## religionOrthodox Christian
## 0.761516508
## religionProtestant
## 1.174812676
## religionOther Christian
## 0.876232166
## religionOther
## 0.453321737
## religionMuslim
## 1.997077577
## religionNon-believers
## 0.979303553
## nonEU_national1
## 0.690148654
## phone_accessLandline only
## 0.895177305
## phone_accessLandline & mobile
## 1.040514134
## phone_accessNo telephone
## 0.606132435
## bill_issuesFrom time to time
## 1.261863952
## bill_issuesAlmost never/never
## 1.580036385
## internet_useTwo or three times a week
## 1.202538557
## internet_useAbout once a week
## 1.548620752
## internet_useTwo or three times a month
## 0.205822438
## internet_useLess often
## 1.082401205
## internet_useNever/No access
## 1.337550906
## internet_useNo Internet access at all
## 1.366822298
## life_satFairly satisfied
## 1.054685123
## life_satNot very satisfied
## 1.338345661
## life_satNot at all satisfied
## 1.005618084
## polintrMedium
## 1.084013516
## polintrLow
## 1.134678895
## polintrNot at all
## 0.955679809
## left_right(5 - 6) Centre
## 1.130183275
## left_right(7 -10) Right
## 1.099231740
## social_alienation
## 1.132173128
## ethnic_minority1
## 1.585950517
## skincolor_minority1
## 0.395659376
## religious_minority1
## 0.616543469
## roma_minority1
## 0.791340592
## sexual_minority1
## 0.650987925
## disability_minority1
## 1.321797816
## suffered_discr1
## 0.683231382
## gender_docsNo
## 1.709613372
## friends_transNo
## 0.927536237
## friends_transRefusal (SPONTANEOUS)
## 1.159127418
## n_friends_minorities
## 1.037755175
## n_actions_against_discri
## 0.860352034
## antilgbtq_rights
## 1.057477224
## minority_discri
## 0.971433339
## country_nameBelgium
## 0.347421173
## country_nameBulgaria
## 3.519418325
## country_nameCroatia
## 0.993092912
## country_nameCyprus
## 1.856208043
## country_nameCzechia
## 1.065640125
## country_nameDenmark
## 1.020965585
## country_nameEstonia
## 1.645499121
## country_nameFinland
## 1.659691425
## country_nameFrance
## 1.233003664
## country_nameGermany
## 1.735979599
## country_nameGreece
## 1.168625297
## country_nameHungary
## 0.818975930
## country_nameIreland
## 1.043881063
## country_nameItaly
## 1.295477566
## country_nameLatvia
## 1.987397162
## country_nameLithuania
## 1.125375345
## country_nameLuxembourg
## 0.977153472
## country_nameMalta
## 0.538315374
## country_nameNetherlands
## 0.721830044
## country_namePoland
## 1.651040115
## country_namePortugal
## 0.712123337
## country_nameRomania
## 0.976758747
## country_nameSlovakia
## 1.283136036
## country_nameSlovenia
## 1.163574636
## country_nameSpain
## 0.677063226
## country_nameSweden
## 2.274838960
## country_nameUnited Kingdom
## 1.724509350Approach to test relationship to DK with splitting and undersampling:
# create new dataset with just vars we want, including age^2
dk_target2 <- dk_target |>
select(target_NA, age, antilgbtq_rights, internet_use, social_class, country_name) |>
mutate(age_sq = age*age, .after = age)
# to deal with some class imbalance, undersample from the majority group (NA = 0)
set.seed(123)
# Generate an index
index <- createDataPartition(dk_target2$target_NA, p = 0.7, list = FALSE, times = 1)
# Subset the dataframe
train <- dk_target2[index, ]
test <- dk_target2[-index, ]
# check splits
prop.table(table(train$target_NA))##
## 0 1
## 0.8787421 0.1212579prop.table(table(test$target_NA))##
## 0 1
## 0.8844612 0.1155388Now undersample the majority
set.seed(123)
under <- ovun.sample(target_NA~.,
data=train,
method = "under",
N = 4000)$data
# limit the sample to 4000 obs as we have ~2300 for target minority class.
table(under$target_NA)##
## 0 1
## 2112 1888#run the rf model
rfunder <- randomForest(target_NA~., data=under)## Warning in randomForest.default(m, y, ...): The response has five or fewer
## unique values. Are you sure you want to do regression?rfunder##
## Call:
## randomForest(formula = target_NA ~ ., data = under)
## Type of random forest: regression
## Number of trees: 500
## No. of variables tried at each split: 2
##
## Mean of squared residuals: 0.2389922
## % Var explained: 4.1We see that only around 5% of the variance is explained.
Testing the NA values against paradata
Here we extend the model to see if paradata is related to changed non-response.
para <- paradata |>
bind_cols(trans_docs = data$trans_docs,
age = data$age,
gender = data$gender,
country = data$country) |>
mutate(target_NA = ifelse(is.na(trans_docs), 1, 0)) |>
select(-serialid, -trans_docs)
summary(para$target_NA)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.0000 0.0000 0.0000 0.1195 0.0000 1.0000str(para)## tibble [27,438 × 9] (S3: tbl_df/tbl/data.frame)
## $ p2 : Factor w/ 6 levels "Before 8 h","8 - 12 h",..: 4 4 3 4 2 4 5 2 4 4 ...
## ..- attr(*, "label")= chr "TIME OF INTERVIEW"
## $ p3 : Factor w/ 246 levels "2 minutes","3",..: 44 39 37 30 30 25 26 33 39 39 ...
## ..- attr(*, "label")= chr "DURATION OF INTERVIEW"
## $ p3r : Factor w/ 7 levels "Up to 14 minutes",..: 4 3 3 3 3 2 2 3 3 3 ...
## ..- attr(*, "label")= chr "DURATION OF INTERVIEW (RECODED)"
## $ p4 : Factor w/ 5 levels "Two (interviewer and respondent)",..: 1 1 1 1 1 1 1 1 1 1 ...
## ..- attr(*, "label")= chr "N OF PERSONS PRESENT DURING INTERVIEW"
## $ p5 : Factor w/ 5 levels "Excellent","Fair",..: 1 1 1 1 1 1 1 1 1 1 ...
## ..- attr(*, "label")= chr "RESPONDENT COOPERATION"
## $ age : num [1:27438] 51 62 38 29 63 41 48 88 44 45 ...
## $ gender : Factor w/ 2 levels "Man","Woman": 1 2 2 1 2 2 1 1 2 2 ...
## $ country : chr [1:27438] "BE" "BE" "BE" "BE" ...
## $ target_NA: num [1:27438] 0 0 0 0 0 0 0 0 0 0 ...First, again test correlation. We use Cramers V since we only have factors:
target_var <- "target_NA"
para_vars <- names(para)[names(para) != target_var]
cramers_v_results <- list()
for (variable in para_vars) {
contingency_table <- table(para[[target_var]],
para[[variable]])
contingency_table_no_dk <- contingency_table[, colnames(contingency_table) != "DK"]
cramers_v <- CramerV(contingency_table_no_dk)
# include this for no DK as it is all zero which creates errors
cramers_v_results[[variable]] <- cramers_v
}
# Create a Tibble for Results
tibble(variable = names(cramers_v_results),
cramers_v = unlist(cramers_v_results)) |>
arrange(desc(cramers_v))## # A tibble: 8 × 2
## variable cramers_v
## <chr> <dbl>
## 1 country 0.168
## 2 age 0.123
## 3 p5 0.106
## 4 p3 0.0916
## 5 gender 0.0292
## 6 p4 0.0165
## 7 p2 0.0116
## 8 p3r 0.0113Again, we see low correlation with the paradata and cramers V.
Second, we run another logistic model with just Paradata included.
na_para_model <- glm(target_NA ~ p2 + p3r + p4 + p5 + age + I(age*age) + gender + factor(country),
data = para,
family=binomial(link = "logit"))
broom::tidy(na_para_model) |>
filter(p.value<0.05) |>
mutate(oddsratio = exp(estimate)) |>
select(term, oddsratio, p.value)## # A tibble: 25 × 3
## term oddsratio p.value
## <chr> <dbl> <dbl>
## 1 (Intercept) 0.0439 4.65e-12
## 2 p4Four 0.694 4.20e- 2
## 3 p5Fair 1.42 2.05e-15
## 4 p5Average 1.74 8.91e-18
## 5 p5Bad 3.49 2.14e-22
## 6 age 0.983 2.85e- 3
## 7 I(age * age) 1.00 3.43e- 9
## 8 genderWoman 1.14 1.07e- 3
## 9 factor(country)BE 0.179 6.77e- 9
## 10 factor(country)BG 5.30 2.16e-31
## # ℹ 15 more rowsWe see that when controlling for age, gender and country, the survey cooperation variable is significant.
When compared to those with an excellent cooperation rating, people were more likely to respond. This increases with lacking cooperation. If cooperation was fair, there was around 40% more chance of NA, if cooperation was average, around 75% higher chance of NA. If cooperation was bad, there was about 350% higher chance of a NA response to our target variable.
Overall, the correlations with our target variables are low which means we don’t have a major concern. Some are interesting e.g. interview cooperation. The worse the cooperation, the more likely to not respond to the question. This could be underreporting No votes, because as we saw in the descriptive analysis, the worse the cooperation, the higher the No vote for supporting trans_docs. There could also be some reverse causality, as not responding leads to a worse cooperation score. But the odds ratios here are very high.
Imputing missing data
As we have different types of variables we decide to go with the default methods. Selecting the best method for each type of variable would be too computationally intensive
# Excluding target variable and other useless variables
imputation_data <- data |>
select(-c(serialid, country, trans_docs))
# Running it with the default methods
imputed_data <- mice(imputation_data, m = 1, seed=1234)##
## iter imp variable
## 1 1 years_edu community marital_status social_class religion bill_issues life_sat left_right social_alienation gender_docs friends_trans antilgbtq_rights minority_discri
## 2 1 years_edu community marital_status social_class religion bill_issues life_sat left_right social_alienation gender_docs friends_trans antilgbtq_rights minority_discri
## 3 1 years_edu community marital_status social_class religion bill_issues life_sat left_right social_alienation gender_docs friends_trans antilgbtq_rights minority_discri
## 4 1 years_edu community marital_status social_class religion bill_issues life_sat left_right social_alienation gender_docs friends_trans antilgbtq_rights minority_discri
## 5 1 years_edu community marital_status social_class religion bill_issues life_sat left_right social_alienation gender_docs friends_trans antilgbtq_rights minority_discri# By default: numerical variables -> pmm, binary factors -> logreg, > 2 levels factors -> polyreg
imputed_data$method## age gender years_edu
## "" "" "pmm"
## community marital_status occupation
## "polyreg" "polyreg" ""
## social_class religion nonEU_national
## "polyreg" "polyreg" ""
## phone_access bill_issues internet_use
## "" "polyreg" ""
## life_sat polintr left_right
## "polyreg" "" "polyreg"
## social_alienation ethnic_minority skincolor_minority
## "pmm" "" ""
## religious_minority roma_minority sexual_minority
## "" "" ""
## disability_minority suffered_discr gender_docs
## "" "" "logreg"
## friends_trans n_friends_minorities n_actions_against_discri
## "polyreg" "" ""
## antilgbtq_rights minority_discri
## "pmm" "pmm"final_data <- complete(imputed_data)
colSums(is.na(imputation_data))## age gender years_edu
## 0 0 387
## community marital_status occupation
## 14 175 0
## social_class religion nonEU_national
## 1021 483 0
## phone_access bill_issues internet_use
## 0 379 0
## life_sat polintr left_right
## 102 0 4689
## social_alienation ethnic_minority skincolor_minority
## 1000 0 0
## religious_minority roma_minority sexual_minority
## 0 0 0
## disability_minority suffered_discr gender_docs
## 0 0 3187
## friends_trans n_friends_minorities n_actions_against_discri
## 968 0 0
## antilgbtq_rights minority_discri
## 791 355colSums(is.na(final_data))## age gender years_edu
## 0 0 0
## community marital_status occupation
## 0 0 0
## social_class religion nonEU_national
## 0 0 0
## phone_access bill_issues internet_use
## 0 0 0
## life_sat polintr left_right
## 0 0 0
## social_alienation ethnic_minority skincolor_minority
## 0 0 0
## religious_minority roma_minority sexual_minority
## 0 0 0
## disability_minority suffered_discr gender_docs
## 0 0 0
## friends_trans n_friends_minorities n_actions_against_discri
## 0 0 0
## antilgbtq_rights minority_discri
## 0 0final_data <- final_data |>
cbind(data$trans_docs) |>
cbind(data$country) |>
rename("trans_docs" = "data$trans_docs",
"country" = "data$country") |>
relocate(country, .before = everything())We know that it would be better to impute multiple datasets and then pool the results of different regressions on those different datasets together, but running more than one multilevel regression would be too computationally intensive and so we are not able to do this.
Joining together all our data
country_level_data stores all our data defined at the
country level.
final_data stores all our data (after imputation) for
individual level variables.
complete_df <- final_data |>
left_join(country_level_data,
by = join_by(country == iso2c)) |>
select(-c(country.y, iso3c))Explanatory model
To be finished…
Run logistic with all variables and extract only the significant variables
Confirm this is similar to the results we obtain using stepwise regression/lasso regularization
Based on 1 & 2 decide which individual level variables to include in the mixed model
Build the mixed model (look at the mixed model section for further details on how this needs to be built)
Simple logistic regression
I am using only individual level data for now. This is a simple model to see at the global level i.e. no country level control, which variables are significant. The numeric data has also been scaled.
datalr <- final_data |>
# Dropping NAs (there should be NAs only in our target variable)
drop_na() |>
# Selecting only predictor variables
select(-"country") |>
# Scale variables
mutate(across(where(is.numeric), scale)) |>
# Transforming target to binary numeric Yes=1, No=0
mutate(trans_docs = as.numeric(trans_docs == "Yes"))
# now run the full model
simple_logistic <- glm(trans_docs ~ ., data = datalr, family = binomial(link = "logit"))
# Save the summary
logistic_summary <- summary(simple_logistic)
# create a tibble to more easily search through significant variables
logistic_results <- tibble(
broom::tidy(simple_logistic) |>
filter(p.value<0.05) |>
mutate(oddsratio = exp(estimate)) |>
select(term, estimate, oddsratio, p.value) |>
arrange(oddsratio))
logistic_results## # A tibble: 26 × 4
## term estimate oddsratio p.value
## <chr> <dbl> <dbl> <dbl>
## 1 gender_docsNo -2.66 0.0697 0
## 2 friends_transRefusal (SPONTANEOUS) -0.798 0.450 2.05e- 5
## 3 antilgbtq_rights -0.699 0.497 1.16e-194
## 4 roma_minority1 -0.568 0.567 1.43e- 4
## 5 internet_useTwo or three times a week -0.418 0.658 4.29e- 8
## 6 life_satNot at all satisfied -0.395 0.673 3.56e- 4
## 7 internet_useNever/No access -0.348 0.706 1.92e- 7
## 8 bill_issuesFrom time to time -0.335 0.716 8.36e- 6
## 9 internet_useAbout once a week -0.332 0.718 2.13e- 2
## 10 occupationRetired (4 in d15a) -0.321 0.725 1.24e- 4
## # ℹ 16 more rowsInterpeting results
To interpret the coefficients as odds ratios, anything above 1 indicates they are more likely to support the changes to civil documents for trans people.
The logistic regression shows that 26 statistically significant terms. This includes factors variables with multiple terms. Of our 29 scaled variables, the significant variables (at the 5% level) are:
More likely to OPPPOSE the right to change civil documents for trans
people, include:
- men (compared to wom) - younger people - people who oppose legal
rights to add a third-gender in official docs (compared to those who do)
- people who refused to answer whether they have trans friends (compared
to those who do) - people who are more financially sound (have fewer
bill issues) - people not satisfied with their life (compared to those
who are ‘very satisfied’) - people who identified as roma or an ethnic
minority - people who are more discriminatory against minorities
More likely to SUPPORT the the right - older people - women - people who were self-employed (compared to all other occupation types incl students) - unmarried (single) people - non-believers (religious) - people with a landline and mobile - people who use the internet everyday/almost everyday (compared to all other internet use categories) - people who reported being more left wing (compared to right wing) - people who had friends in minority groups.
NUMERIC VARIABLES
Without scaling, we interpret logistic regression output as:
coef(simple_logistic): these coefficients represent the
change in the log-odds for a one-unit increase in the corresponding
independent variable
exp(coef(simple_logistic)): the exponential of the slope
coefficient (exp(B)) tells us the change of the odds if the independent
variable increases by one unit
If the data is scaled:
A coefficient B (from a logistic regression) now reflects the change in the log-odds for a one standard deviation increase in the predictor variable, rather than a one-unit increase in the original scale.
The odds ratio (exp(B)) now tells you how the odds change with a one standard deviation increase in the predictor variable, rather than a one-unit increase.
Here we compare the pre and post transformation of coefficients for interpretation:
# all the coefficients
head(coef(simple_logistic))## (Intercept) age
## 2.69303178 0.20879798
## genderWoman years_edu
## 0.26342657 -0.01215087
## communitySmall or middle sized town communityLarge town
## 0.01810837 -0.04039684# for their interpretation
head(exp(coef(simple_logistic)))## (Intercept) age
## 14.7764069 1.2321960
## genderWoman years_edu
## 1.3013817 0.9879227
## communitySmall or middle sized town communityLarge town
## 1.0182733 0.9604082FACTOR VARIABLES
Factor variables when exponentialised give the likelihood to respond
no/yes relative to the base group in the factor variable. We use the
function factors to view the levels and identify the base
group.
To assist with interpretation of factor outputs:
Here is a function to identify all the base levels in each factor group. Useful to refer to during analysis of different logistic models.
extract_base_groups <- function(df) {
# extract factor vars only and list to print values
factor_vars <- names(final_data)[sapply(final_data, is.factor)]
base_groups <- list()
# loop through values to check all levels
for (var in factor_vars) {
if (length(levels(df[[var]])) > 0) { # Check step - should be TRUE for all selected.
contrast_matrix <- contrasts(df[[var]])
if (is.null(contrast_matrix)) {
base_groups[[var]] <- levels(df[[var]])[1] # check only - shouldn't ever run
} else {
base_group_level <- levels(df[[var]])[rowSums(abs(contrast_matrix)) == 0] # base group is the one with all zeroes, so we extract that
base_groups[[var]] <- base_group_level
}
} else {
base_groups[[var]] <- NA # Indicate non-factor or factor with no levels.
}
}
return(base_groups)
}
# run function with 'final data' and print a tidy output
factor_bases <- extract_base_groups(final_data)
factor_bases <- as_tibble(factor_bases) |>
pivot_longer(cols = everything(),
names_to = "vars",
values_to = "base_group")
factor_bases## # A tibble: 23 × 2
## vars base_group
## <chr> <chr>
## 1 gender Man
## 2 community Rural area or village
## 3 marital_status (Re-)Married (1-4 in d7)
## 4 occupation Self-employed (5 to 9 in d15a)
## 5 social_class The working class of society
## 6 religion Catholic
## 7 nonEU_national 0
## 8 phone_access Mobile only
## 9 bill_issues Most of the time
## 10 internet_use Everyday/Almost everyday
## # ℹ 13 more rowsModel performance - Simple logistic
Here, we test the models ability to classify people as supporting or not supporting the rights.
# AIC of model
simple_logistic$aic## [1] 19544.18#predicted probabilities of being a 1 (i.e. a refusal of possibility of trans doc)
predicted_probs <- simple_logistic$fitted.values
# same by running
# predicted_probs <- predict(simple_logistic, type = "response")
head(predicted_probs)## 1 2 3 4 5 6
## 0.3463520 0.4321645 0.5170989 0.5799662 0.9141149 0.5131253# Turning them to classes using custom threshold
predicted_classes <- ifelse(predicted_probs > 0.5, 1, 0)
head(predicted_classes)## 1 2 3 4 5 6
## 0 0 1 1 1 1Get the confusion matrix:
confusionMatrix(as.factor(datalr$trans_docs), as.factor(predicted_classes))## Confusion Matrix and Statistics
##
## Reference
## Prediction 0 1
## 0 7608 2087
## 1 2246 12217
##
## Accuracy : 0.8206
## 95% CI : (0.8157, 0.8255)
## No Information Rate : 0.5921
## P-Value [Acc > NIR] : < 2e-16
##
## Kappa : 0.6277
##
## Mcnemar's Test P-Value : 0.01638
##
## Sensitivity : 0.7721
## Specificity : 0.8541
## Pos Pred Value : 0.7847
## Neg Pred Value : 0.8447
## Prevalence : 0.4079
## Detection Rate : 0.3149
## Detection Prevalence : 0.4013
## Balanced Accuracy : 0.8131
##
## 'Positive' Class : 0
## The simple model predicted people’s response with 82% accuracy. That is quite decent for a basic first model. This shows the response is quite explainable with the data we have. The model is slightly better at predicting those who do not support than those who do. Seen by higher specificity than sensitivity (85% vs 77%). But they are both comparable which is good and confirms we don’t have great class imbalance.
roc_obj <- roc(datalr$trans_docs, predicted_probs)## Setting levels: control = 0, case = 1## Setting direction: controls < cases# Terrible graphs, do we have better ones? Not sure. I think the first is good enough.
pROC::ggroc(roc_obj)
plot(roc_obj)
coords(roc_obj, "best")## threshold specificity sensitivity
## 1 0.5937607 0.843115 0.7938187auc(datalr$trans_docs, predicted_probs)## Setting levels: control = 0, case = 1
## Setting direction: controls < cases## Area under the curve: 0.8937Stepwise regression
Chooses the best simple logistic model based on the lowest AIC achievable
set.seed(123)
stepAIC <- step(simple_logistic, direction = "both", trace=0)
stepAIC##
## Call: glm(formula = trans_docs ~ age + gender + marital_status + occupation +
## religion + phone_access + bill_issues + internet_use + life_sat +
## left_right + ethnic_minority + roma_minority + suffered_discr +
## gender_docs + friends_trans + n_friends_minorities + n_actions_against_discri +
## antilgbtq_rights + minority_discri, family = binomial(link = "logit"),
## data = datalr)
##
## Coefficients:
## (Intercept)
## 2.62467
## age
## 0.20698
## genderWoman
## 0.26440
## marital_statusSingle living with partner (5-8 in d7)
## 0.04042
## marital_statusSingle (9-10 in d7)
## 0.13987
## marital_statusDivorced or separated (11-12 in d7)
## 0.10517
## marital_statusWidow (13-14 in d7)
## -0.10979
## occupationManagers (10 to 12 in d15a)
## 0.01744
## occupationOther white collars (13 or 14 in d15a)
## -0.25937
## occupationManual workers (15 to 18 in d15a)
## -0.14375
## occupationHouse persons (1 in d15a)
## 0.05889
## occupationUnemployed (3 in d15a)
## -0.12589
## occupationRetired (4 in d15a)
## -0.30665
## occupationStudents (2 in d15a)
## -0.29364
## religionOrthodox Christian
## -0.12432
## religionProtestant
## 0.08546
## religionOther Christian
## -0.13836
## religionOther
## 0.06244
## religionMuslim
## -0.24374
## religionNon-believers
## 0.13104
## phone_accessLandline only
## -0.09735
## phone_accessLandline & mobile
## 0.27311
## phone_accessNo telephone
## -0.19336
## bill_issuesFrom time to time
## -0.34079
## bill_issuesAlmost never/never
## -0.22203
## internet_useTwo or three times a week
## -0.41597
## internet_useAbout once a week
## -0.31328
## internet_useTwo or three times a month
## -0.09201
## internet_useLess often
## 0.02229
## internet_useNever/No access
## -0.33028
## internet_useNo Internet access at all
## -0.02332
## life_satFairly satisfied
## 0.05142
## life_satNot very satisfied
## -0.14512
## life_satNot at all satisfied
## -0.38741
## left_right(5 - 6) Centre
## 0.05631
## left_right(7 -10) Right
## -0.17298
## ethnic_minority1
## -0.26298
## roma_minority1
## -0.58673
## suffered_discr1
## -0.22381
## gender_docsNo
## -2.65983
## friends_transNo
## -0.13252
## friends_transRefusal (SPONTANEOUS)
## -0.79810
## n_friends_minorities
## 0.15912
## n_actions_against_discri
## 0.03980
## antilgbtq_rights
## -0.69753
## minority_discri
## -0.23593
##
## Degrees of Freedom: 24157 Total (i.e. Null); 24112 Residual
## Null Deviance: 32540
## Residual Deviance: 19430 AIC: 19530The stepwise regression has 19 of the 29 variables included in it’s best model. It is quite consistent with what our significant variables were above, so we will not provide further commentary. Compared to the full model, this reduced model does not provide a statistically significant improvement in fit. But it does give us a more simple model and shows us what individual level variable may be most important overall.
anova(simple_logistic, stepAIC)## Analysis of Deviance Table
##
## Model 1: trans_docs ~ age + gender + years_edu + community + marital_status +
## occupation + social_class + religion + nonEU_national + phone_access +
## bill_issues + internet_use + life_sat + polintr + left_right +
## social_alienation + ethnic_minority + skincolor_minority +
## religious_minority + roma_minority + sexual_minority + disability_minority +
## suffered_discr + gender_docs + friends_trans + n_friends_minorities +
## n_actions_against_discri + antilgbtq_rights + minority_discri
## Model 2: trans_docs ~ age + gender + marital_status + occupation + religion +
## phone_access + bill_issues + internet_use + life_sat + left_right +
## ethnic_minority + roma_minority + suffered_discr + gender_docs +
## friends_trans + n_friends_minorities + n_actions_against_discri +
## antilgbtq_rights + minority_discri
## Resid. Df Resid. Dev Df Deviance Pr(>Chi)
## 1 24096 19420
## 2 24112 19434 -16 -14.121 0.5897DIEGO: ask for an explanation of this
Lasso regularization
We still have too many variables for a mixed model. So here we will use Lasso to keep only our most important variables for the mixed models.
Without this step, the glmer stage is too computationally expensive.
lasso_data <- final_data |>
# Doing same preprocessing as done for simple logistic
drop_na() |>
select(-"country") |>
mutate(across(where(is.numeric), scale)) |>
mutate(trans_docs = as.numeric(trans_docs == "Yes"))
# Dummifying all levels to see whether some levels are particularly important
lasso_data <- lasso_data %>%
dummy_cols(select_columns = names(.)[sapply(., is.factor)],
remove_selected_columns = TRUE,
remove_first_dummy = TRUE)
# Convert data into a matrix for glmnet
x_lasso <- lasso_data |> select(-trans_docs) |> as.matrix()
y_lasso <- lasso_data |> select(trans_docs) |> as.matrix()
set.seed(123)
# Define lamdas
lambda_seq <- 10^seq(-2, -5, length.out = 100)
# Fit the Lasso model (alpha = 1 for Lasso regularization)
lasso_model <- cv.glmnet(x_lasso, y_lasso, family = "binomial", alpha = 1, lambda = lambda_seq)
lasso_model$lambda.1se # The largest lambda within one standard error of lambda.min. This results in a simpler model with fewer selected features.## [1] 0.007564633lasso_model$lambda.min## [1] 0.0006579332# Get all the coefficients
coefficients <- coef(lasso_model, s = "lambda.1se")
# Filter for the non-zero ones
non_zero_features <- rownames(coefficients)[which(coefficients != 0)]
non_zero_features## [1] "(Intercept)"
## [2] "age"
## [3] "n_friends_minorities"
## [4] "antilgbtq_rights"
## [5] "minority_discri"
## [6] "gender_Woman"
## [7] "occupation_Managers (10 to 12 in d15a)"
## [8] "religion_Orthodox Christian"
## [9] "phone_access_Landline & mobile"
## [10] "bill_issues_From time to time"
## [11] "internet_use_Two or three times a week"
## [12] "internet_use_Never/No access"
## [13] "life_sat_Not very satisfied"
## [14] "life_sat_Not at all satisfied"
## [15] "left_right_(7 -10) Right"
## [16] "ethnic_minority_1"
## [17] "roma_minority_1"
## [18] "suffered_discr_1"
## [19] "gender_docs_No"
## [20] "friends_trans_Refusal (SPONTANEOUS)"Lasso includes variables similar to what was suggested by our initial logistic regression and the subsequent stepwise.
In particular we can see again that:
ageis relevantgenderis relevantIt matters whether you have friends that belong to minorites (
n_friends_minorities)
Also `ant
Final variable selection
From these hints above and general intuition, we will select the following variables as our individual level fixed effects in the mixed level model:
- age
- gender
- religion (to be recoded as non-believer dummy since that’s the significant variable)
- bill_issues
- internet use (recoded to everyday or not)
- left_right
- ethnic minority + roma minority (recoded to one dummy)
- trans_friends
- lgbti_docs
- minority_discri
And these are our pre-defined fixed
Mixed model
Random Intercept Model:
Allows the baseline level (intercept) to vary across groups. Assumes the relationship between predictors and outcome (slope) is the same for all groups
In R syntax: y ~ x + (1|group)
Example: Different schools might have different average test scores (random intercepts), but the effect of study hours on test scores is the same across all schools
Random Slope Model:
Allows the effect of a predictor (slope) to vary across groups. Can be used with or without random intercepts.
In R syntax: y ~ x + (0+x|group) for random slope only, or y ~ x + (1+x|group) for both random intercept and slope
Example: The effect of study hours on test scores might be stronger in some schools than others (random slopes)
Random intercept models account for different baselines between groups, while random slope models account for different relationships between predictors and outcomes across groups. When both random intercepts and slopes are included, you’re allowing both the baseline and the effect of predictors to vary by group.
Interactions between group-level (higher-level) variables and individual-level (lower-level) variables in mixed models are called cross-level interactions.
Cross-level interactions are particularly useful in multilevel research because they help you understand how the relationship between an individual-level predictor and the outcome varies as a function of a group-level characteristic.
For example, in educational research: 1) Individual level: student characteristics (study time, prior knowledge). 2) Group level: school or classroom characteristics (class size, teaching method). 3) Cross-level interaction: Does the effect of study time on performance depend on class size?
Running the glmer models
To model, we will follow: Approach to multilevel model building based on Hox (2010)
1/ Null Model (Random Intercept only) 2/ Add independent Level 1 variables 3/ Add independent Level 2 variables 4/ Add random slopes 5/ (Cross-level) interactions
Each step, check whether your model is significantly improved compared to the previous one.
We could run these different models and select the best one: null_glmer -> only country random effects for a baseline glmer_stepwise -> using the best stepwise model best model for individual fixed effects + adding country random effects glmer_lasso -> using the lasso model fixed individual level effects + country glmer_level2 -> using the best model from above and adding in all country level fixed effects too glmer_cross_level -> the model using integrated
# Switching to df containing both individual and country level
complete_df <- complete_df |>
drop_na() # should be zero as we cleaned before but just in case
# Scaling the variables speeds up the running time. However we loose interpretation? maybe the best thing to do is to center them rather than scaling?
scaled_df <- complete_df |>
mutate(across(where(is.numeric), scale))
# include glmer null model for comparison for improvements - only has random intercept
null_glmer_model <- glmer(trans_docs ~ (1|country),
data = scaled_df,
family=binomial(link="logit"))
## running the level 1 glmer model (indiviudal fixed effects + country random effects)
# variable selection from the stepwise model output
# this took 7.6 minutes to run WITH the scaled data, saved output locally
# start <- Sys.time()
# glmer_model_level1 <- glmer(
# # target
# trans_docs ~
# #individual data - significant from stepwise testing
# age + gender + marital_status + occupation +
# religion + phone_access + bill_issues + internet_use + life_sat +
# left_right + ethnic_minority + roma_minority + suffered_discr +
# gender_docs + friends_trans + n_friends_minorities + n_actions_against_discri +
# antilgbtq_rights + minority_discri + (1|country),
# data = scaled_df,
# family = binomial(link="logit")
# )
# end <- Sys.time()
# end-start
# glmer_model_level1
# output_glmer_1 <- broom.mixed::tidy(glmer_model_level1)
## running the level 2 glmer model (individual & country fixed effects + country random effects)
# took 10.8 minutes to run so commented out. Saved output locally
# start <- Sys.time()
# glmer_model_level2 <- glmer(
# # target variable
# trans_docs ~
# #individual level fixed effects
# age + gender + marital_status + occupation +
# religion + phone_access + bill_issues + internet_use + life_sat +
# left_right + ethnic_minority + roma_minority + suffered_discr +
# gender_docs + friends_trans + n_friends_minorities + n_actions_against_discri +
# antilgbtq_rights + minority_discri +
# #country level fixed effects
# gdp_pc_ppp + gender_inequality_index + lgbt_policy_index + democracy_index +
# # random effects of country
# (1|country),
# data = scaled_df,
# family = binomial(link="logit")
# )
# end <- Sys.time()
# end-start
# output_glmer_2 <- broom.mixed::tidy(glmer_model_level2)
# glmer model with cross-level interactions
glmer_model <- glmer(trans_docs ~ gender:lgbt_policy_index + gender*gender_inequality_index + religion*gdp_pc_ppp + (1 | country), data=scaled_df, family=binomial(link="logit"))
## saving the level1 and level2 outputs to file for review of full model effects
#write_csv2(output_glmer_1, "glmer_level1_model_output.csv")
#write_csv2(output_glmer_2, "glmer_level2_model_output.csv")
## writing output for AIC/BIC and saving too
# glmer_compare <- anova(null_glmer_model, glmer_model_level1, glmer_model_level2, glmer_model)
# write_csv2(glmer_compare, "glmer_compare_basicmodels.csv")
#variable1*variable2 includes both the two variables separetely and their interaction
#variable1:variable2 includes only the interaction
#+ (1|country) country is the grouping variable, means it includes different intercepts for each country
summary(glmer_model) # print in better tables as Marga likes## Generalized linear mixed model fit by maximum likelihood (Laplace
## Approximation) [glmerMod]
## Family: binomial ( logit )
## Formula:
## trans_docs ~ gender:lgbt_policy_index + gender * gender_inequality_index +
## religion * gdp_pc_ppp + (1 | country)
## Data: scaled_df
##
## AIC BIC logLik deviance df.resid
## 27760.0 27921.9 -13860.0 27720.0 24138
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -2.7415 -0.6925 -0.4228 0.8840 4.3145
##
## Random effects:
## Groups Name Variance Std.Dev.
## country (Intercept) 0.2811 0.5302
## Number of obs: 24158, groups: country, 28
##
## Fixed effects:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -0.13257 0.10594 -1.251 0.210790
## genderWoman -0.45316 0.03005 -15.078 < 2e-16 ***
## gender_inequality_index 0.24293 0.13636 1.782 0.074811 .
## religionOrthodox Christian 0.14645 0.08192 1.788 0.073834 .
## religionProtestant -0.13893 0.06647 -2.090 0.036598 *
## religionOther Christian 0.12569 0.07722 1.628 0.103615
## religionOther -0.21752 0.07083 -3.071 0.002132 **
## religionMuslim 0.30066 0.12738 2.360 0.018262 *
## religionNon-believers -0.56485 0.04552 -12.408 < 2e-16 ***
## gdp_pc_ppp -0.17013 0.10547 -1.613 0.106709
## genderMan:lgbt_policy_index -0.43634 0.12755 -3.421 0.000624 ***
## genderWoman:lgbt_policy_index -0.56816 0.12745 -4.458 8.27e-06 ***
## genderWoman:gender_inequality_index 0.03763 0.04140 0.909 0.363389
## religionOrthodox Christian:gdp_pc_ppp 0.16989 0.09191 1.848 0.064558 .
## religionProtestant:gdp_pc_ppp 0.15569 0.08005 1.945 0.051789 .
## religionOther Christian:gdp_pc_ppp 0.04970 0.08085 0.615 0.538751
## religionOther:gdp_pc_ppp 0.10349 0.06960 1.487 0.137031
## religionMuslim:gdp_pc_ppp 0.24136 0.12339 1.956 0.050455 .
## religionNon-believers:gdp_pc_ppp 0.01368 0.04643 0.295 0.768327
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1##
## Correlation matrix not shown by default, as p = 19 > 12.
## Use print(x, correlation=TRUE) or
## vcov(x) if you need it# To calculate the intraclass coefficient (ICC) for the model, we use the ICC function from performance.
# Calculate ICC for the null model, we get around 22% explained
performance::icc(null_glmer_model)## # Intraclass Correlation Coefficient
##
## Adjusted ICC: 0.227
## Unadjusted ICC: 0.227# When we run for the model with scaled data, we get 7% ICC
performance::icc(glmer_model)## # Intraclass Correlation Coefficient
##
## Adjusted ICC: 0.079
## Unadjusted ICC: 0.064# this gives us the following significant variables: age, gender, occupation, religion, phone_access, bill_issues, internet_use, left_right, ethnic_minority_
# we exclude these non significant variable: martial_status, The idea is to run interactions between individual level variables and country level variables choosing pair which make sense (ex. does the effect of being female on support for trans docs depend on the gender equality index? –> did this by doing gender*gender_inequality_index)
Let’s use our brain and common sense to choose the best combinations
Predictive model
Summarize individual data to a country level (ex. percentage of population living in rural areas by country, percentage of people from minority x by country)
Run random forest/gradient boosting/logistic regression with leave-one-out cross validation
Leave-One-Out Cross-Validation (LOOCV): LOOCV is a special case of k-fold cross-validation, where k = the number of observations (n).
That means: For each observation (1 out of 28), the model is trained on the remaining 27 rows and tested on the left-out row. This process repeats 28 times (once per row). The final performance metric (e.g., accuracy, RMSE) is the average of all 28 test results.
Aggregating individual data to country level
We should be building a dataframe with 28 rows (1 per country), but many variables (ex, percentage of christian people by country, percentage of very satisfied with lives people by country, percentage of people that belong to the roma minority etc.; our target variable would become % of people that support trans_docs by country)
In the next steps we will synthesize the information from the individual respondents into country-level variables.
Using means for numeric variables:
names(select(final_data, where(is.numeric))) # using final_data because it still has "country", which we dropped for complete_df## [1] "age" "years_edu"
## [3] "social_alienation" "n_friends_minorities"
## [5] "n_actions_against_discri" "antilgbtq_rights"
## [7] "minority_discri"data_num <- final_data |>
group_by(country) |>
summarise(across(where(is.numeric), ~mean(.), .names = "mean_{.col}"))As well as for dummies:
# searching for factor variables with two levels
dummy_names <- names(final_data)[sapply(final_data, is.factor) & sapply(final_data, function(x) length(levels(x)) == 2)]
dummy_names## [1] "gender" "nonEU_national" "ethnic_minority"
## [4] "skincolor_minority" "religious_minority" "roma_minority"
## [7] "sexual_minority" "disability_minority" "suffered_discr"
## [10] "gender_docs" "trans_docs"dummy_levels <- lapply(final_data[dummy_names], levels)
dummy_levels## $gender
## [1] "Man" "Woman"
##
## $nonEU_national
## [1] "0" "1"
##
## $ethnic_minority
## [1] "0" "1"
##
## $skincolor_minority
## [1] "0" "1"
##
## $religious_minority
## [1] "0" "1"
##
## $roma_minority
## [1] "0" "1"
##
## $sexual_minority
## [1] "0" "1"
##
## $disability_minority
## [1] "0" "1"
##
## $suffered_discr
## [1] "0" "1"
##
## $gender_docs
## [1] "Yes" "No"
##
## $trans_docs
## [1] "Yes" "No"colSums(is.na(final_data[dummy_names]))## gender nonEU_national ethnic_minority skincolor_minority
## 0 0 0 0
## religious_minority roma_minority sexual_minority disability_minority
## 0 0 0 0
## suffered_discr gender_docs trans_docs
## 0 0 3280After imputations only the target variable should have NAs. They have already been dropped before so no variable has NAs
data_dummy <- final_data %>%
select(country, all_of(dummy_names)) %>%
mutate(across(all_of(dummy_names),
~ case_when(
. %in% c("0", "1") ~ as.numeric(as.character(.)), # convert "0"/"1" to 0/1
. %in% c("Yes", "No") ~ recode(., "Yes" = 1, "No" = 0), # convert "Yes"/"No" to 1/0
. %in% c("Man", "Woman") ~ recode(., "Man" = 1, "Woman" = 0), # convert "Man"/"Woman" to 1/0
TRUE ~ NA # assign NA to other unexpected values
),
.names = "{.col}_num"))## Warning: There were 3 warnings in `mutate()`.
## The first warning was:
## ℹ In argument: `across(...)`.
## Caused by warning:
## ! NAs introduced by coercion
## ℹ Run `dplyr::last_dplyr_warnings()` to see the 2 remaining warnings.colSums(is.na(data_dummy)) # The warning is weird as there seem to be no NAs## country gender nonEU_national
## 0 0 0
## ethnic_minority skincolor_minority religious_minority
## 0 0 0
## roma_minority sexual_minority disability_minority
## 0 0 0
## suffered_discr gender_docs trans_docs
## 0 0 3280
## gender_num nonEU_national_num ethnic_minority_num
## 0 0 0
## skincolor_minority_num religious_minority_num roma_minority_num
## 0 0 0
## sexual_minority_num disability_minority_num suffered_discr_num
## 0 0 0
## gender_docs_num trans_docs_num
## 0 3280I converted factors with 2 levels to numerical 0-1 so we can compute their means.
Deleted the column calculating the % of NAs in trans_doc because although useful those NAs had already been dropped so it was returning all 0s
# country means
data_dummy <- data_dummy %>%
group_by(country) %>%
summarise(
across(ends_with("_num"), ~ mean(.x, na.rm = TRUE)),
.groups = "drop"
)
# substitute the "_num" suffix with a "mean_" prefix so it has the same format as the variables in data_num
data_dummy <- data_dummy %>%
rename_with(~ paste0("mean_", str_remove(., "_num$")), ends_with("_num"))
colSums(is.na(data_dummy))## country mean_gender mean_nonEU_national
## 0 0 0
## mean_ethnic_minority mean_skincolor_minority mean_religious_minority
## 0 0 0
## mean_roma_minority mean_sexual_minority mean_disability_minority
## 0 0 0
## mean_suffered_discr mean_gender_docs mean_trans_docs
## 0 0 0Now we can join the two datasets.
data_aggr <- data_num %>%
left_join(data_dummy, by = "country")The next variables are factor with >2 levels:
factor_names <- names(final_data)[!sapply(final_data, is.numeric) &
!(sapply(final_data, is.factor) & sapply(final_data, function(x) length(levels(x)) == 2))]
factor_names## [1] "country" "community" "marital_status" "occupation"
## [5] "social_class" "religion" "phone_access" "bill_issues"
## [9] "internet_use" "life_sat" "polintr" "left_right"
## [13] "friends_trans"# checking the levels
lapply(final_data[factor_names], levels)## $country
## NULL
##
## $community
## [1] "Rural area or village" "Small or middle sized town"
## [3] "Large town"
##
## $marital_status
## [1] "(Re-)Married (1-4 in d7)"
## [2] "Single living with partner (5-8 in d7)"
## [3] "Single (9-10 in d7)"
## [4] "Divorced or separated (11-12 in d7)"
## [5] "Widow (13-14 in d7)"
##
## $occupation
## [1] "Self-employed (5 to 9 in d15a)"
## [2] "Managers (10 to 12 in d15a)"
## [3] "Other white collars (13 or 14 in d15a)"
## [4] "Manual workers (15 to 18 in d15a)"
## [5] "House persons (1 in d15a)"
## [6] "Unemployed (3 in d15a)"
## [7] "Retired (4 in d15a)"
## [8] "Students (2 in d15a)"
##
## $social_class
## [1] "The working class of society" "The lower middle class of society"
## [3] "The middle class of society" "The upper middle class of society"
## [5] "The higher class of society"
##
## $religion
## [1] "Catholic" "Orthodox Christian" "Protestant"
## [4] "Other Christian" "Other" "Muslim"
## [7] "Non-believers"
##
## $phone_access
## [1] "Mobile only" "Landline only" "Landline & mobile"
## [4] "No telephone"
##
## $bill_issues
## [1] "Most of the time" "From time to time" "Almost never/never"
##
## $internet_use
## [1] "Everyday/Almost everyday" "Two or three times a week"
## [3] "About once a week" "Two or three times a month"
## [5] "Less often" "Never/No access"
## [7] "No Internet access at all"
##
## $life_sat
## [1] "Very satisfied" "Fairly satisfied" "Not very satisfied"
## [4] "Not at all satisfied"
##
## $polintr
## [1] "Strong" "Medium" "Low" "Not at all"
##
## $left_right
## [1] "(1 - 4) Left" "(5 - 6) Centre" "(7 -10) Right"
##
## $friends_trans
## [1] "Yes" "No" "Refusal (SPONTANEOUS)"# removing country from the list
factor_names <- setdiff(factor_names, "country")
# creating the aggregated dataset for factor variables
data_factors <- final_data %>%
select(country, all_of(factor_names)) %>%
pivot_longer(cols = -country, names_to = "variable", values_to = "level") %>%
group_by(country, variable, level) %>%
summarise(count = n(), .groups = "drop") %>%
group_by(country, variable) %>%
mutate(proportion = count / sum(count)) %>%
select(-count) %>%
pivot_wider(names_from = c(variable, level), values_from = proportion, names_glue = "{variable}_{level}")
colSums(is.na(data_factors))## country
## 0
## bill_issues_Most of the time
## 0
## bill_issues_From time to time
## 0
## bill_issues_Almost never/never
## 0
## community_Rural area or village
## 0
## community_Small or middle sized town
## 0
## community_Large town
## 0
## friends_trans_Yes
## 0
## friends_trans_No
## 0
## friends_trans_Refusal (SPONTANEOUS)
## 0
## internet_use_Everyday/Almost everyday
## 0
## internet_use_Two or three times a week
## 0
## internet_use_About once a week
## 1
## internet_use_Two or three times a month
## 0
## internet_use_Less often
## 0
## internet_use_Never/No access
## 0
## internet_use_No Internet access at all
## 0
## left_right_(1 - 4) Left
## 0
## left_right_(5 - 6) Centre
## 0
## left_right_(7 -10) Right
## 0
## life_sat_Very satisfied
## 0
## life_sat_Fairly satisfied
## 0
## life_sat_Not very satisfied
## 0
## life_sat_Not at all satisfied
## 0
## marital_status_(Re-)Married (1-4 in d7)
## 0
## marital_status_Single living with partner (5-8 in d7)
## 0
## marital_status_Single (9-10 in d7)
## 0
## marital_status_Divorced or separated (11-12 in d7)
## 0
## marital_status_Widow (13-14 in d7)
## 0
## occupation_Self-employed (5 to 9 in d15a)
## 0
## occupation_Managers (10 to 12 in d15a)
## 0
## occupation_Other white collars (13 or 14 in d15a)
## 0
## occupation_Manual workers (15 to 18 in d15a)
## 0
## occupation_House persons (1 in d15a)
## 0
## occupation_Unemployed (3 in d15a)
## 0
## occupation_Retired (4 in d15a)
## 0
## occupation_Students (2 in d15a)
## 0
## phone_access_Mobile only
## 0
## phone_access_Landline only
## 0
## phone_access_Landline & mobile
## 0
## phone_access_No telephone
## 1
## polintr_Strong
## 0
## polintr_Medium
## 0
## polintr_Low
## 0
## polintr_Not at all
## 0
## religion_Catholic
## 0
## religion_Orthodox Christian
## 0
## religion_Protestant
## 1
## religion_Other Christian
## 2
## religion_Other
## 0
## religion_Muslim
## 4
## religion_Non-believers
## 0
## social_class_The working class of society
## 0
## social_class_The lower middle class of society
## 0
## social_class_The middle class of society
## 0
## social_class_The upper middle class of society
## 0
## social_class_The higher class of society
## 3We are seeing NAs because in not all countries are all the factors’ levels represented. For example we see that social_class_The higher class of society has 3 missing values. Let’s confirm that there are 3 countries in our dataframe with no observation for that level
final_data |> filter(social_class=="The higher class of society") |> pull(country) |> unique() |> length()## [1] 25Therefore those proportions should be 0s and not NAs
data_factors <- data_factors |>
mutate(across(everything(), ~replace_na(., 0)))Joining all together
data_aggr <- data_aggr |>
left_join(data_factors, by = "country")Lastly, joining the country level variables obtained from external sources
data_aggr <- data_aggr |>
left_join(country_level_data, by = c("country" = "iso2c")) |>
select(-c(iso3c, country.y))colSums(is.na(data_aggr))## country
## 0
## mean_age
## 0
## mean_years_edu
## 0
## mean_social_alienation
## 0
## mean_n_friends_minorities
## 0
## mean_n_actions_against_discri
## 0
## mean_antilgbtq_rights
## 0
## mean_minority_discri
## 0
## mean_gender
## 0
## mean_nonEU_national
## 0
## mean_ethnic_minority
## 0
## mean_skincolor_minority
## 0
## mean_religious_minority
## 0
## mean_roma_minority
## 0
## mean_sexual_minority
## 0
## mean_disability_minority
## 0
## mean_suffered_discr
## 0
## mean_gender_docs
## 0
## mean_trans_docs
## 0
## bill_issues_Most of the time
## 0
## bill_issues_From time to time
## 0
## bill_issues_Almost never/never
## 0
## community_Rural area or village
## 0
## community_Small or middle sized town
## 0
## community_Large town
## 0
## friends_trans_Yes
## 0
## friends_trans_No
## 0
## friends_trans_Refusal (SPONTANEOUS)
## 0
## internet_use_Everyday/Almost everyday
## 0
## internet_use_Two or three times a week
## 0
## internet_use_About once a week
## 0
## internet_use_Two or three times a month
## 0
## internet_use_Less often
## 0
## internet_use_Never/No access
## 0
## internet_use_No Internet access at all
## 0
## left_right_(1 - 4) Left
## 0
## left_right_(5 - 6) Centre
## 0
## left_right_(7 -10) Right
## 0
## life_sat_Very satisfied
## 0
## life_sat_Fairly satisfied
## 0
## life_sat_Not very satisfied
## 0
## life_sat_Not at all satisfied
## 0
## marital_status_(Re-)Married (1-4 in d7)
## 0
## marital_status_Single living with partner (5-8 in d7)
## 0
## marital_status_Single (9-10 in d7)
## 0
## marital_status_Divorced or separated (11-12 in d7)
## 0
## marital_status_Widow (13-14 in d7)
## 0
## occupation_Self-employed (5 to 9 in d15a)
## 0
## occupation_Managers (10 to 12 in d15a)
## 0
## occupation_Other white collars (13 or 14 in d15a)
## 0
## occupation_Manual workers (15 to 18 in d15a)
## 0
## occupation_House persons (1 in d15a)
## 0
## occupation_Unemployed (3 in d15a)
## 0
## occupation_Retired (4 in d15a)
## 0
## occupation_Students (2 in d15a)
## 0
## phone_access_Mobile only
## 0
## phone_access_Landline only
## 0
## phone_access_Landline & mobile
## 0
## phone_access_No telephone
## 0
## polintr_Strong
## 0
## polintr_Medium
## 0
## polintr_Low
## 0
## polintr_Not at all
## 0
## religion_Catholic
## 0
## religion_Orthodox Christian
## 0
## religion_Protestant
## 0
## religion_Other Christian
## 0
## religion_Other
## 0
## religion_Muslim
## 0
## religion_Non-believers
## 0
## social_class_The working class of society
## 0
## social_class_The lower middle class of society
## 0
## social_class_The middle class of society
## 0
## social_class_The upper middle class of society
## 0
## social_class_The higher class of society
## 0
## gdp_pc_ppp
## 0
## gender_inequality_index
## 0
## lgbt_policy_index
## 0
## democracy_index
## 0dim(data_aggr)## [1] 28 79The resulting data frame has 28 observations and 79 variables. We might have to clean the names of the variables that were glued from variable_level.
Linear regression with LASSO
data_lasso <- data_aggr |>
select(-country)
# Define the leave-one-out cross-validation control
ctrl <- trainControl(
method = "LOOCV",
verboseIter = TRUE
)
# Set up the grid of lambda values for Lasso
lambda_grid <- 10^seq(-3, 3, length = 100)
# Train the Lasso model with LOOCV
lasso_model <- train(
mean_trans_docs ~ .,
data = data_lasso,
method = "glmnet",
preProc=c('scale','center'),
trControl = ctrl,
tuneGrid = expand.grid(
alpha = 1, # 1 for Lasso
lambda = lambda_grid
),
importance = TRUE,
metric = "RMSE"
)## + Fold01: alpha=1, lambda=1000
## - Fold01: alpha=1, lambda=1000
## + Fold02: alpha=1, lambda=1000
## - Fold02: alpha=1, lambda=1000
## + Fold03: alpha=1, lambda=1000
## - Fold03: alpha=1, lambda=1000
## + Fold04: alpha=1, lambda=1000
## - Fold04: alpha=1, lambda=1000
## + Fold05: alpha=1, lambda=1000
## - Fold05: alpha=1, lambda=1000
## + Fold06: alpha=1, lambda=1000
## - Fold06: alpha=1, lambda=1000
## + Fold07: alpha=1, lambda=1000
## - Fold07: alpha=1, lambda=1000
## + Fold08: alpha=1, lambda=1000
## - Fold08: alpha=1, lambda=1000
## + Fold09: alpha=1, lambda=1000
## - Fold09: alpha=1, lambda=1000
## + Fold10: alpha=1, lambda=1000
## - Fold10: alpha=1, lambda=1000
## + Fold11: alpha=1, lambda=1000
## - Fold11: alpha=1, lambda=1000
## + Fold12: alpha=1, lambda=1000
## - Fold12: alpha=1, lambda=1000
## + Fold13: alpha=1, lambda=1000
## - Fold13: alpha=1, lambda=1000
## + Fold14: alpha=1, lambda=1000
## - Fold14: alpha=1, lambda=1000
## + Fold15: alpha=1, lambda=1000
## - Fold15: alpha=1, lambda=1000
## + Fold16: alpha=1, lambda=1000
## - Fold16: alpha=1, lambda=1000
## + Fold17: alpha=1, lambda=1000
## - Fold17: alpha=1, lambda=1000
## + Fold18: alpha=1, lambda=1000
## - Fold18: alpha=1, lambda=1000
## + Fold19: alpha=1, lambda=1000
## - Fold19: alpha=1, lambda=1000
## + Fold20: alpha=1, lambda=1000
## - Fold20: alpha=1, lambda=1000
## + Fold21: alpha=1, lambda=1000
## - Fold21: alpha=1, lambda=1000
## + Fold22: alpha=1, lambda=1000
## - Fold22: alpha=1, lambda=1000
## + Fold23: alpha=1, lambda=1000
## - Fold23: alpha=1, lambda=1000
## + Fold24: alpha=1, lambda=1000
## - Fold24: alpha=1, lambda=1000
## + Fold25: alpha=1, lambda=1000
## - Fold25: alpha=1, lambda=1000
## + Fold26: alpha=1, lambda=1000
## - Fold26: alpha=1, lambda=1000
## + Fold27: alpha=1, lambda=1000
## - Fold27: alpha=1, lambda=1000
## + Fold28: alpha=1, lambda=1000
## - Fold28: alpha=1, lambda=1000
## Aggregating results
## Selecting tuning parameters
## Fitting alpha = 1, lambda = 0.0163 on full training set# Print the best tuning parameter (lambda)
print(lasso_model$bestTune)## alpha lambda
## 21 1 0.01629751# Summarize the final model
print(lasso_model)## glmnet
##
## 28 samples
## 77 predictors
##
## Pre-processing: scaled (77), centered (77)
## Resampling: Leave-One-Out Cross-Validation
## Summary of sample sizes: 27, 27, 27, 27, 27, 27, ...
## Resampling results across tuning parameters:
##
## lambda RMSE Rsquared MAE
## 1.000000e-03 0.10383281 0.7527260 0.08758219
## 1.149757e-03 0.10383281 0.7527260 0.08758219
## 1.321941e-03 0.10383281 0.7527260 0.08758219
## 1.519911e-03 0.10383281 0.7527260 0.08758219
## 1.747528e-03 0.10383281 0.7527260 0.08758219
## 2.009233e-03 0.10402767 0.7519423 0.08791975
## 2.310130e-03 0.10461221 0.7500256 0.08952507
## 2.656088e-03 0.10360276 0.7549616 0.08982328
## 3.053856e-03 0.10231113 0.7624769 0.08967178
## 3.511192e-03 0.10071627 0.7705257 0.08859326
## 4.037017e-03 0.09876515 0.7782737 0.08675034
## 4.641589e-03 0.09754309 0.7815376 0.08562794
## 5.336699e-03 0.09480301 0.7921722 0.08391056
## 6.135907e-03 0.08979748 0.8129860 0.07892787
## 7.054802e-03 0.08490749 0.8329937 0.07373353
## 8.111308e-03 0.08063554 0.8496713 0.06929678
## 9.326033e-03 0.07783049 0.8604324 0.06648746
## 1.072267e-02 0.07582093 0.8683450 0.06447392
## 1.232847e-02 0.07390484 0.8764899 0.06262299
## 1.417474e-02 0.07231164 0.8837525 0.06063496
## 1.629751e-02 0.07201306 0.8869303 0.05990110
## 1.873817e-02 0.07246559 0.8880918 0.06086861
## 2.154435e-02 0.07298646 0.8894410 0.06187848
## 2.477076e-02 0.07402423 0.8899153 0.06317244
## 2.848036e-02 0.07510115 0.8912782 0.06420057
## 3.274549e-02 0.07642657 0.8933710 0.06528348
## 3.764936e-02 0.07859592 0.8951661 0.06696827
## 4.328761e-02 0.08167235 0.8966355 0.06883089
## 4.977024e-02 0.08576341 0.8978095 0.07156834
## 5.722368e-02 0.09156221 0.8959180 0.07534686
## 6.579332e-02 0.09916970 0.8891343 0.08056696
## 7.564633e-02 0.10875071 0.8757446 0.08875632
## 8.697490e-02 0.11946558 0.8570995 0.09796251
## 1.000000e-01 0.13020231 0.8477038 0.10672825
## 1.149757e-01 0.14338089 0.8352499 0.11705874
## 1.321941e-01 0.15934474 0.8112914 0.13075534
## 1.519911e-01 0.17824636 0.7442530 0.14682227
## 1.747528e-01 0.20049562 0.2980089 0.16535467
## 2.009233e-01 0.21473400 1.0000000 0.18063976
## 2.310130e-01 0.21473400 1.0000000 0.18063976
## 2.656088e-01 0.21473400 1.0000000 0.18063976
## 3.053856e-01 0.21473400 1.0000000 0.18063976
## 3.511192e-01 0.21473400 1.0000000 0.18063976
## 4.037017e-01 0.21473400 1.0000000 0.18063976
## 4.641589e-01 0.21473400 1.0000000 0.18063976
## 5.336699e-01 0.21473400 1.0000000 0.18063976
## 6.135907e-01 0.21473400 1.0000000 0.18063976
## 7.054802e-01 0.21473400 1.0000000 0.18063976
## 8.111308e-01 0.21473400 1.0000000 0.18063976
## 9.326033e-01 0.21473400 1.0000000 0.18063976
## 1.072267e+00 0.21473400 1.0000000 0.18063976
## 1.232847e+00 0.21473400 1.0000000 0.18063976
## 1.417474e+00 0.21473400 1.0000000 0.18063976
## 1.629751e+00 0.21473400 1.0000000 0.18063976
## 1.873817e+00 0.21473400 1.0000000 0.18063976
## 2.154435e+00 0.21473400 1.0000000 0.18063976
## 2.477076e+00 0.21473400 1.0000000 0.18063976
## 2.848036e+00 0.21473400 1.0000000 0.18063976
## 3.274549e+00 0.21473400 1.0000000 0.18063976
## 3.764936e+00 0.21473400 1.0000000 0.18063976
## 4.328761e+00 0.21473400 1.0000000 0.18063976
## 4.977024e+00 0.21473400 1.0000000 0.18063976
## 5.722368e+00 0.21473400 1.0000000 0.18063976
## 6.579332e+00 0.21473400 1.0000000 0.18063976
## 7.564633e+00 0.21473400 1.0000000 0.18063976
## 8.697490e+00 0.21473400 1.0000000 0.18063976
## 1.000000e+01 0.21473400 1.0000000 0.18063976
## 1.149757e+01 0.21473400 1.0000000 0.18063976
## 1.321941e+01 0.21473400 1.0000000 0.18063976
## 1.519911e+01 0.21473400 1.0000000 0.18063976
## 1.747528e+01 0.21473400 1.0000000 0.18063976
## 2.009233e+01 0.21473400 1.0000000 0.18063976
## 2.310130e+01 0.21473400 1.0000000 0.18063976
## 2.656088e+01 0.21473400 1.0000000 0.18063976
## 3.053856e+01 0.21473400 1.0000000 0.18063976
## 3.511192e+01 0.21473400 1.0000000 0.18063976
## 4.037017e+01 0.21473400 1.0000000 0.18063976
## 4.641589e+01 0.21473400 1.0000000 0.18063976
## 5.336699e+01 0.21473400 1.0000000 0.18063976
## 6.135907e+01 0.21473400 1.0000000 0.18063976
## 7.054802e+01 0.21473400 1.0000000 0.18063976
## 8.111308e+01 0.21473400 1.0000000 0.18063976
## 9.326033e+01 0.21473400 1.0000000 0.18063976
## 1.072267e+02 0.21473400 1.0000000 0.18063976
## 1.232847e+02 0.21473400 1.0000000 0.18063976
## 1.417474e+02 0.21473400 1.0000000 0.18063976
## 1.629751e+02 0.21473400 1.0000000 0.18063976
## 1.873817e+02 0.21473400 1.0000000 0.18063976
## 2.154435e+02 0.21473400 1.0000000 0.18063976
## 2.477076e+02 0.21473400 1.0000000 0.18063976
## 2.848036e+02 0.21473400 1.0000000 0.18063976
## 3.274549e+02 0.21473400 1.0000000 0.18063976
## 3.764936e+02 0.21473400 1.0000000 0.18063976
## 4.328761e+02 0.21473400 1.0000000 0.18063976
## 4.977024e+02 0.21473400 1.0000000 0.18063976
## 5.722368e+02 0.21473400 1.0000000 0.18063976
## 6.579332e+02 0.21473400 1.0000000 0.18063976
## 7.564633e+02 0.21473400 1.0000000 0.18063976
## 8.697490e+02 0.21473400 1.0000000 0.18063976
## 1.000000e+03 0.21473400 1.0000000 0.18063976
##
## Tuning parameter 'alpha' was held constant at a value of 1
## RMSE was used to select the optimal model using the smallest value.
## The final values used for the model were alpha = 1 and lambda = 0.01629751.# Examine variable importance
importance <- varImp(lasso_model, scale = FALSE)
print(importance)## glmnet variable importance
##
## only 20 most important variables shown (out of 77)
##
## Overall
## mean_gender_docs 0.129202
## mean_roma_minority 0.032442
## mean_antilgbtq_rights 0.015207
## `friends_trans_Refusal (SPONTANEOUS)` 0.015012
## `life_sat_Not at all satisfied` 0.009104
## `phone_access_No telephone` 0.004799
## `internet_use_Two or three times a week` 0.004144
## mean_nonEU_national 0.003555
## democracy_index 0.001031
## `religion_Non-believers` 0.000000
## mean_suffered_discr 0.000000
## `internet_use_Never/No access` 0.000000
## `occupation_Unemployed (3 in d15a)` 0.000000
## `social_class_The higher class of society` 0.000000
## `religion_Other Christian` 0.000000
## `internet_use_About once a week` 0.000000
## mean_religious_minority 0.000000
## `life_sat_Very satisfied` 0.000000
## `phone_access_Mobile only` 0.000000
## `internet_use_Everyday/Almost everyday` 0.000000plot(importance, top = 20)
# Get the coefficients of the best model
best_model <- lasso_model$finalModel
#coef_lasso <- coef(best_model) giving me errors
#print(coef_lasso)
# Calculate predictions and residuals
predictions <- predict(lasso_model, data_lasso)
# Extract the actual values
actual <- data_lasso$mean_trans_docs
# Calculate residuals
residuals <- actual - predictions
# Calculate R-squared and RMSE
r_squared <- 1 - sum(residuals^2) / sum((actual - mean(actual))^2)
rmse <- sqrt(mean(residuals^2))
cat("R-squared:", r_squared, "\n")## R-squared: 0.9470027cat("RMSE:", rmse, "\n")## RMSE: 0.04766869# Plot actual vs predicted values
plot(actual, predictions,
main = "Actual vs Predicted Values",
xlab = "Actual", ylab = "Predicted",
pch = 16, col = "blue")
abline(0, 1, col = "red")
# Plot residuals
plot(predictions, residuals,
main = "Residuals vs Predicted Values",
xlab = "Predicted Values", ylab = "Residuals",
pch = 16, col = "blue")
abline(h = 0, col = "red")
# Combine country names with predictions
# Giving me errrors
# country_predictions <- data.frame(
# country = data_aggr$country,
# actual = target,
# predicted = predictions
# )
# # Sort by prediction (descending)
# Giving me errors
# country_predictions <- country_predictions[order(country_predictions$predicted, decreasing = TRUE), ]
# print(country_predictions)Random forest
data_aggr <- data_aggr |>
select(-country)
# Define LOOCV control
control <- trainControl(
method = "LOOCV",
verboseIter = TRUE, # Print progress
returnResamp = "all" # Save all resampling results
)
# Define hyperparameter grid for Random Forest
rf_grid <- expand.grid(
mtry = seq(2, ncol(data_aggr) - 1, by = 2)
)
# mtry the number of variables randomly sampled at each split
# Train Random Forest model with hyperparameter tuning
rf_model <- train(
mean_trans_docs ~ .,
data = data_aggr,
method = "rf",
preProc=c('scale','center'),
trControl = control,
tuneGrid = rf_grid,
importance = TRUE # Calculate variable importance
)## + Fold01: mtry= 2
## - Fold01: mtry= 2
## + Fold01: mtry= 4
## - Fold01: mtry= 4
## + Fold01: mtry= 6
## - Fold01: mtry= 6
## + Fold01: mtry= 8
## - Fold01: mtry= 8
## + Fold01: mtry=10
## - Fold01: mtry=10
## + Fold01: mtry=12
## - Fold01: mtry=12
## + Fold01: mtry=14
## - Fold01: mtry=14
## + Fold01: mtry=16
## - Fold01: mtry=16
## + Fold01: mtry=18
## - Fold01: mtry=18
## + Fold01: mtry=20
## - Fold01: mtry=20
## + Fold01: mtry=22
## - Fold01: mtry=22
## + Fold01: mtry=24
## - Fold01: mtry=24
## + Fold01: mtry=26
## - Fold01: mtry=26
## + Fold01: mtry=28
## - Fold01: mtry=28
## + Fold01: mtry=30
## - Fold01: mtry=30
## + Fold01: mtry=32
## - Fold01: mtry=32
## + Fold01: mtry=34
## - Fold01: mtry=34
## + Fold01: mtry=36
## - Fold01: mtry=36
## + Fold01: mtry=38
## - Fold01: mtry=38
## + Fold01: mtry=40
## - Fold01: mtry=40
## + Fold01: mtry=42
## - Fold01: mtry=42
## + Fold01: mtry=44
## - Fold01: mtry=44
## + Fold01: mtry=46
## - Fold01: mtry=46
## + Fold01: mtry=48
## - Fold01: mtry=48
## + Fold01: mtry=50
## - Fold01: mtry=50
## + Fold01: mtry=52
## - Fold01: mtry=52
## + Fold01: mtry=54
## - Fold01: mtry=54
## + Fold01: mtry=56
## - Fold01: mtry=56
## + Fold01: mtry=58
## - Fold01: mtry=58
## + Fold01: mtry=60
## - Fold01: mtry=60
## + Fold01: mtry=62
## - Fold01: mtry=62
## + Fold01: mtry=64
## - Fold01: mtry=64
## + Fold01: mtry=66
## - Fold01: mtry=66
## + Fold01: mtry=68
## - Fold01: mtry=68
## + Fold01: mtry=70
## - Fold01: mtry=70
## + Fold01: mtry=72
## - Fold01: mtry=72
## + Fold01: mtry=74
## - Fold01: mtry=74
## + Fold01: mtry=76
## - Fold01: mtry=76
## + Fold02: mtry= 2
## - Fold02: mtry= 2
## + Fold02: mtry= 4
## - Fold02: mtry= 4
## + Fold02: mtry= 6
## - Fold02: mtry= 6
## + Fold02: mtry= 8
## - Fold02: mtry= 8
## + Fold02: mtry=10
## - Fold02: mtry=10
## + Fold02: mtry=12
## - Fold02: mtry=12
## + Fold02: mtry=14
## - Fold02: mtry=14
## + Fold02: mtry=16
## - Fold02: mtry=16
## + Fold02: mtry=18
## - Fold02: mtry=18
## + Fold02: mtry=20
## - Fold02: mtry=20
## + Fold02: mtry=22
## - Fold02: mtry=22
## + Fold02: mtry=24
## - Fold02: mtry=24
## + Fold02: mtry=26
## - Fold02: mtry=26
## + Fold02: mtry=28
## - Fold02: mtry=28
## + Fold02: mtry=30
## - Fold02: mtry=30
## + Fold02: mtry=32
## - Fold02: mtry=32
## + Fold02: mtry=34
## - Fold02: mtry=34
## + Fold02: mtry=36
## - Fold02: mtry=36
## + Fold02: mtry=38
## - Fold02: mtry=38
## + Fold02: mtry=40
## - Fold02: mtry=40
## + Fold02: mtry=42
## - Fold02: mtry=42
## + Fold02: mtry=44
## - Fold02: mtry=44
## + Fold02: mtry=46
## - Fold02: mtry=46
## + Fold02: mtry=48
## - Fold02: mtry=48
## + Fold02: mtry=50
## - Fold02: mtry=50
## + Fold02: mtry=52
## - Fold02: mtry=52
## + Fold02: mtry=54
## - Fold02: mtry=54
## + Fold02: mtry=56
## - Fold02: mtry=56
## + Fold02: mtry=58
## - Fold02: mtry=58
## + Fold02: mtry=60
## - Fold02: mtry=60
## + Fold02: mtry=62
## - Fold02: mtry=62
## + Fold02: mtry=64
## - Fold02: mtry=64
## + Fold02: mtry=66
## - Fold02: mtry=66
## + Fold02: mtry=68
## - Fold02: mtry=68
## + Fold02: mtry=70
## - Fold02: mtry=70
## + Fold02: mtry=72
## - Fold02: mtry=72
## + Fold02: mtry=74
## - Fold02: mtry=74
## + Fold02: mtry=76
## - Fold02: mtry=76
## + Fold03: mtry= 2
## - Fold03: mtry= 2
## + Fold03: mtry= 4
## - Fold03: mtry= 4
## + Fold03: mtry= 6
## - Fold03: mtry= 6
## + Fold03: mtry= 8
## - Fold03: mtry= 8
## + Fold03: mtry=10
## - Fold03: mtry=10
## + Fold03: mtry=12
## - Fold03: mtry=12
## + Fold03: mtry=14
## - Fold03: mtry=14
## + Fold03: mtry=16
## - Fold03: mtry=16
## + Fold03: mtry=18
## - Fold03: mtry=18
## + Fold03: mtry=20
## - Fold03: mtry=20
## + Fold03: mtry=22
## - Fold03: mtry=22
## + Fold03: mtry=24
## - Fold03: mtry=24
## + Fold03: mtry=26
## - Fold03: mtry=26
## + Fold03: mtry=28
## - Fold03: mtry=28
## + Fold03: mtry=30
## - Fold03: mtry=30
## + Fold03: mtry=32
## - Fold03: mtry=32
## + Fold03: mtry=34
## - Fold03: mtry=34
## + Fold03: mtry=36
## - Fold03: mtry=36
## + Fold03: mtry=38
## - Fold03: mtry=38
## + Fold03: mtry=40
## - Fold03: mtry=40
## + Fold03: mtry=42
## - Fold03: mtry=42
## + Fold03: mtry=44
## - Fold03: mtry=44
## + Fold03: mtry=46
## - Fold03: mtry=46
## + Fold03: mtry=48
## - Fold03: mtry=48
## + Fold03: mtry=50
## - Fold03: mtry=50
## + Fold03: mtry=52
## - Fold03: mtry=52
## + Fold03: mtry=54
## - Fold03: mtry=54
## + Fold03: mtry=56
## - Fold03: mtry=56
## + Fold03: mtry=58
## - Fold03: mtry=58
## + Fold03: mtry=60
## - Fold03: mtry=60
## + Fold03: mtry=62
## - Fold03: mtry=62
## + Fold03: mtry=64
## - Fold03: mtry=64
## + Fold03: mtry=66
## - Fold03: mtry=66
## + Fold03: mtry=68
## - Fold03: mtry=68
## + Fold03: mtry=70
## - Fold03: mtry=70
## + Fold03: mtry=72
## - Fold03: mtry=72
## + Fold03: mtry=74
## - Fold03: mtry=74
## + Fold03: mtry=76
## - Fold03: mtry=76
## + Fold04: mtry= 2
## - Fold04: mtry= 2
## + Fold04: mtry= 4
## - Fold04: mtry= 4
## + Fold04: mtry= 6
## - Fold04: mtry= 6
## + Fold04: mtry= 8
## - Fold04: mtry= 8
## + Fold04: mtry=10
## - Fold04: mtry=10
## + Fold04: mtry=12
## - Fold04: mtry=12
## + Fold04: mtry=14
## - Fold04: mtry=14
## + Fold04: mtry=16
## - Fold04: mtry=16
## + Fold04: mtry=18
## - Fold04: mtry=18
## + Fold04: mtry=20
## - Fold04: mtry=20
## + Fold04: mtry=22
## - Fold04: mtry=22
## + Fold04: mtry=24
## - Fold04: mtry=24
## + Fold04: mtry=26
## - Fold04: mtry=26
## + Fold04: mtry=28
## - Fold04: mtry=28
## + Fold04: mtry=30
## - Fold04: mtry=30
## + Fold04: mtry=32
## - Fold04: mtry=32
## + Fold04: mtry=34
## - Fold04: mtry=34
## + Fold04: mtry=36
## - Fold04: mtry=36
## + Fold04: mtry=38
## - Fold04: mtry=38
## + Fold04: mtry=40
## - Fold04: mtry=40
## + Fold04: mtry=42
## - Fold04: mtry=42
## + Fold04: mtry=44
## - Fold04: mtry=44
## + Fold04: mtry=46
## - Fold04: mtry=46
## + Fold04: mtry=48
## - Fold04: mtry=48
## + Fold04: mtry=50
## - Fold04: mtry=50
## + Fold04: mtry=52
## - Fold04: mtry=52
## + Fold04: mtry=54
## - Fold04: mtry=54
## + Fold04: mtry=56
## - Fold04: mtry=56
## + Fold04: mtry=58
## - Fold04: mtry=58
## + Fold04: mtry=60
## - Fold04: mtry=60
## + Fold04: mtry=62
## - Fold04: mtry=62
## + Fold04: mtry=64
## - Fold04: mtry=64
## + Fold04: mtry=66
## - Fold04: mtry=66
## + Fold04: mtry=68
## - Fold04: mtry=68
## + Fold04: mtry=70
## - Fold04: mtry=70
## + Fold04: mtry=72
## - Fold04: mtry=72
## + Fold04: mtry=74
## - Fold04: mtry=74
## + Fold04: mtry=76
## - Fold04: mtry=76
## + Fold05: mtry= 2
## - Fold05: mtry= 2
## + Fold05: mtry= 4
## - Fold05: mtry= 4
## + Fold05: mtry= 6
## - Fold05: mtry= 6
## + Fold05: mtry= 8
## - Fold05: mtry= 8
## + Fold05: mtry=10
## - Fold05: mtry=10
## + Fold05: mtry=12
## - Fold05: mtry=12
## + Fold05: mtry=14
## - Fold05: mtry=14
## + Fold05: mtry=16
## - Fold05: mtry=16
## + Fold05: mtry=18
## - Fold05: mtry=18
## + Fold05: mtry=20
## - Fold05: mtry=20
## + Fold05: mtry=22
## - Fold05: mtry=22
## + Fold05: mtry=24
## - Fold05: mtry=24
## + Fold05: mtry=26
## - Fold05: mtry=26
## + Fold05: mtry=28
## - Fold05: mtry=28
## + Fold05: mtry=30
## - Fold05: mtry=30
## + Fold05: mtry=32
## - Fold05: mtry=32
## + Fold05: mtry=34
## - Fold05: mtry=34
## + Fold05: mtry=36
## - Fold05: mtry=36
## + Fold05: mtry=38
## - Fold05: mtry=38
## + Fold05: mtry=40
## - Fold05: mtry=40
## + Fold05: mtry=42
## - Fold05: mtry=42
## + Fold05: mtry=44
## - Fold05: mtry=44
## + Fold05: mtry=46
## - Fold05: mtry=46
## + Fold05: mtry=48
## - Fold05: mtry=48
## + Fold05: mtry=50
## - Fold05: mtry=50
## + Fold05: mtry=52
## - Fold05: mtry=52
## + Fold05: mtry=54
## - Fold05: mtry=54
## + Fold05: mtry=56
## - Fold05: mtry=56
## + Fold05: mtry=58
## - Fold05: mtry=58
## + Fold05: mtry=60
## - Fold05: mtry=60
## + Fold05: mtry=62
## - Fold05: mtry=62
## + Fold05: mtry=64
## - Fold05: mtry=64
## + Fold05: mtry=66
## - Fold05: mtry=66
## + Fold05: mtry=68
## - Fold05: mtry=68
## + Fold05: mtry=70
## - Fold05: mtry=70
## + Fold05: mtry=72
## - Fold05: mtry=72
## + Fold05: mtry=74
## - Fold05: mtry=74
## + Fold05: mtry=76
## - Fold05: mtry=76
## + Fold06: mtry= 2
## - Fold06: mtry= 2
## + Fold06: mtry= 4
## - Fold06: mtry= 4
## + Fold06: mtry= 6
## - Fold06: mtry= 6
## + Fold06: mtry= 8
## - Fold06: mtry= 8
## + Fold06: mtry=10
## - Fold06: mtry=10
## + Fold06: mtry=12
## - Fold06: mtry=12
## + Fold06: mtry=14
## - Fold06: mtry=14
## + Fold06: mtry=16
## - Fold06: mtry=16
## + Fold06: mtry=18
## - Fold06: mtry=18
## + Fold06: mtry=20
## - Fold06: mtry=20
## + Fold06: mtry=22
## - Fold06: mtry=22
## + Fold06: mtry=24
## - Fold06: mtry=24
## + Fold06: mtry=26
## - Fold06: mtry=26
## + Fold06: mtry=28
## - Fold06: mtry=28
## + Fold06: mtry=30
## - Fold06: mtry=30
## + Fold06: mtry=32
## - Fold06: mtry=32
## + Fold06: mtry=34
## - Fold06: mtry=34
## + Fold06: mtry=36
## - Fold06: mtry=36
## + Fold06: mtry=38
## - Fold06: mtry=38
## + Fold06: mtry=40
## - Fold06: mtry=40
## + Fold06: mtry=42
## - Fold06: mtry=42
## + Fold06: mtry=44
## - Fold06: mtry=44
## + Fold06: mtry=46
## - Fold06: mtry=46
## + Fold06: mtry=48
## - Fold06: mtry=48
## + Fold06: mtry=50
## - Fold06: mtry=50
## + Fold06: mtry=52
## - Fold06: mtry=52
## + Fold06: mtry=54
## - Fold06: mtry=54
## + Fold06: mtry=56
## - Fold06: mtry=56
## + Fold06: mtry=58
## - Fold06: mtry=58
## + Fold06: mtry=60
## - Fold06: mtry=60
## + Fold06: mtry=62
## - Fold06: mtry=62
## + Fold06: mtry=64
## - Fold06: mtry=64
## + Fold06: mtry=66
## - Fold06: mtry=66
## + Fold06: mtry=68
## - Fold06: mtry=68
## + Fold06: mtry=70
## - Fold06: mtry=70
## + Fold06: mtry=72
## - Fold06: mtry=72
## + Fold06: mtry=74
## - Fold06: mtry=74
## + Fold06: mtry=76
## - Fold06: mtry=76
## + Fold07: mtry= 2
## - Fold07: mtry= 2
## + Fold07: mtry= 4
## - Fold07: mtry= 4
## + Fold07: mtry= 6
## - Fold07: mtry= 6
## + Fold07: mtry= 8
## - Fold07: mtry= 8
## + Fold07: mtry=10
## - Fold07: mtry=10
## + Fold07: mtry=12
## - Fold07: mtry=12
## + Fold07: mtry=14
## - Fold07: mtry=14
## + Fold07: mtry=16
## - Fold07: mtry=16
## + Fold07: mtry=18
## - Fold07: mtry=18
## + Fold07: mtry=20
## - Fold07: mtry=20
## + Fold07: mtry=22
## - Fold07: mtry=22
## + Fold07: mtry=24
## - Fold07: mtry=24
## + Fold07: mtry=26
## - Fold07: mtry=26
## + Fold07: mtry=28
## - Fold07: mtry=28
## + Fold07: mtry=30
## - Fold07: mtry=30
## + Fold07: mtry=32
## - Fold07: mtry=32
## + Fold07: mtry=34
## - Fold07: mtry=34
## + Fold07: mtry=36
## - Fold07: mtry=36
## + Fold07: mtry=38
## - Fold07: mtry=38
## + Fold07: mtry=40
## - Fold07: mtry=40
## + Fold07: mtry=42
## - Fold07: mtry=42
## + Fold07: mtry=44
## - Fold07: mtry=44
## + Fold07: mtry=46
## - Fold07: mtry=46
## + Fold07: mtry=48
## - Fold07: mtry=48
## + Fold07: mtry=50
## - Fold07: mtry=50
## + Fold07: mtry=52
## - Fold07: mtry=52
## + Fold07: mtry=54
## - Fold07: mtry=54
## + Fold07: mtry=56
## - Fold07: mtry=56
## + Fold07: mtry=58
## - Fold07: mtry=58
## + Fold07: mtry=60
## - Fold07: mtry=60
## + Fold07: mtry=62
## - Fold07: mtry=62
## + Fold07: mtry=64
## - Fold07: mtry=64
## + Fold07: mtry=66
## - Fold07: mtry=66
## + Fold07: mtry=68
## - Fold07: mtry=68
## + Fold07: mtry=70
## - Fold07: mtry=70
## + Fold07: mtry=72
## - Fold07: mtry=72
## + Fold07: mtry=74
## - Fold07: mtry=74
## + Fold07: mtry=76
## - Fold07: mtry=76
## + Fold08: mtry= 2
## - Fold08: mtry= 2
## + Fold08: mtry= 4
## - Fold08: mtry= 4
## + Fold08: mtry= 6
## - Fold08: mtry= 6
## + Fold08: mtry= 8
## - Fold08: mtry= 8
## + Fold08: mtry=10
## - Fold08: mtry=10
## + Fold08: mtry=12
## - Fold08: mtry=12
## + Fold08: mtry=14
## - Fold08: mtry=14
## + Fold08: mtry=16
## - Fold08: mtry=16
## + Fold08: mtry=18
## - Fold08: mtry=18
## + Fold08: mtry=20
## - Fold08: mtry=20
## + Fold08: mtry=22
## - Fold08: mtry=22
## + Fold08: mtry=24
## - Fold08: mtry=24
## + Fold08: mtry=26
## - Fold08: mtry=26
## + Fold08: mtry=28
## - Fold08: mtry=28
## + Fold08: mtry=30
## - Fold08: mtry=30
## + Fold08: mtry=32
## - Fold08: mtry=32
## + Fold08: mtry=34
## - Fold08: mtry=34
## + Fold08: mtry=36
## - Fold08: mtry=36
## + Fold08: mtry=38
## - Fold08: mtry=38
## + Fold08: mtry=40
## - Fold08: mtry=40
## + Fold08: mtry=42
## - Fold08: mtry=42
## + Fold08: mtry=44
## - Fold08: mtry=44
## + Fold08: mtry=46
## - Fold08: mtry=46
## + Fold08: mtry=48
## - Fold08: mtry=48
## + Fold08: mtry=50
## - Fold08: mtry=50
## + Fold08: mtry=52
## - Fold08: mtry=52
## + Fold08: mtry=54
## - Fold08: mtry=54
## + Fold08: mtry=56
## - Fold08: mtry=56
## + Fold08: mtry=58
## - Fold08: mtry=58
## + Fold08: mtry=60
## - Fold08: mtry=60
## + Fold08: mtry=62
## - Fold08: mtry=62
## + Fold08: mtry=64
## - Fold08: mtry=64
## + Fold08: mtry=66
## - Fold08: mtry=66
## + Fold08: mtry=68
## - Fold08: mtry=68
## + Fold08: mtry=70
## - Fold08: mtry=70
## + Fold08: mtry=72
## - Fold08: mtry=72
## + Fold08: mtry=74
## - Fold08: mtry=74
## + Fold08: mtry=76
## - Fold08: mtry=76
## + Fold09: mtry= 2
## - Fold09: mtry= 2
## + Fold09: mtry= 4
## - Fold09: mtry= 4
## + Fold09: mtry= 6
## - Fold09: mtry= 6
## + Fold09: mtry= 8
## - Fold09: mtry= 8
## + Fold09: mtry=10
## - Fold09: mtry=10
## + Fold09: mtry=12
## - Fold09: mtry=12
## + Fold09: mtry=14
## - Fold09: mtry=14
## + Fold09: mtry=16
## - Fold09: mtry=16
## + Fold09: mtry=18
## - Fold09: mtry=18
## + Fold09: mtry=20
## - Fold09: mtry=20
## + Fold09: mtry=22
## - Fold09: mtry=22
## + Fold09: mtry=24
## - Fold09: mtry=24
## + Fold09: mtry=26
## - Fold09: mtry=26
## + Fold09: mtry=28
## - Fold09: mtry=28
## + Fold09: mtry=30
## - Fold09: mtry=30
## + Fold09: mtry=32
## - Fold09: mtry=32
## + Fold09: mtry=34
## - Fold09: mtry=34
## + Fold09: mtry=36
## - Fold09: mtry=36
## + Fold09: mtry=38
## - Fold09: mtry=38
## + Fold09: mtry=40
## - Fold09: mtry=40
## + Fold09: mtry=42
## - Fold09: mtry=42
## + Fold09: mtry=44
## - Fold09: mtry=44
## + Fold09: mtry=46
## - Fold09: mtry=46
## + Fold09: mtry=48
## - Fold09: mtry=48
## + Fold09: mtry=50
## - Fold09: mtry=50
## + Fold09: mtry=52
## - Fold09: mtry=52
## + Fold09: mtry=54
## - Fold09: mtry=54
## + Fold09: mtry=56
## - Fold09: mtry=56
## + Fold09: mtry=58
## - Fold09: mtry=58
## + Fold09: mtry=60
## - Fold09: mtry=60
## + Fold09: mtry=62
## - Fold09: mtry=62
## + Fold09: mtry=64
## - Fold09: mtry=64
## + Fold09: mtry=66
## - Fold09: mtry=66
## + Fold09: mtry=68
## - Fold09: mtry=68
## + Fold09: mtry=70
## - Fold09: mtry=70
## + Fold09: mtry=72
## - Fold09: mtry=72
## + Fold09: mtry=74
## - Fold09: mtry=74
## + Fold09: mtry=76
## - Fold09: mtry=76
## + Fold10: mtry= 2
## - Fold10: mtry= 2
## + Fold10: mtry= 4
## - Fold10: mtry= 4
## + Fold10: mtry= 6
## - Fold10: mtry= 6
## + Fold10: mtry= 8
## - Fold10: mtry= 8
## + Fold10: mtry=10
## - Fold10: mtry=10
## + Fold10: mtry=12
## - Fold10: mtry=12
## + Fold10: mtry=14
## - Fold10: mtry=14
## + Fold10: mtry=16
## - Fold10: mtry=16
## + Fold10: mtry=18
## - Fold10: mtry=18
## + Fold10: mtry=20
## - Fold10: mtry=20
## + Fold10: mtry=22
## - Fold10: mtry=22
## + Fold10: mtry=24
## - Fold10: mtry=24
## + Fold10: mtry=26
## - Fold10: mtry=26
## + Fold10: mtry=28
## - Fold10: mtry=28
## + Fold10: mtry=30
## - Fold10: mtry=30
## + Fold10: mtry=32
## - Fold10: mtry=32
## + Fold10: mtry=34
## - Fold10: mtry=34
## + Fold10: mtry=36
## - Fold10: mtry=36
## + Fold10: mtry=38
## - Fold10: mtry=38
## + Fold10: mtry=40
## - Fold10: mtry=40
## + Fold10: mtry=42
## - Fold10: mtry=42
## + Fold10: mtry=44
## - Fold10: mtry=44
## + Fold10: mtry=46
## - Fold10: mtry=46
## + Fold10: mtry=48
## - Fold10: mtry=48
## + Fold10: mtry=50
## - Fold10: mtry=50
## + Fold10: mtry=52
## - Fold10: mtry=52
## + Fold10: mtry=54
## - Fold10: mtry=54
## + Fold10: mtry=56
## - Fold10: mtry=56
## + Fold10: mtry=58
## - Fold10: mtry=58
## + Fold10: mtry=60
## - Fold10: mtry=60
## + Fold10: mtry=62
## - Fold10: mtry=62
## + Fold10: mtry=64
## - Fold10: mtry=64
## + Fold10: mtry=66
## - Fold10: mtry=66
## + Fold10: mtry=68
## - Fold10: mtry=68
## + Fold10: mtry=70
## - Fold10: mtry=70
## + Fold10: mtry=72
## - Fold10: mtry=72
## + Fold10: mtry=74
## - Fold10: mtry=74
## + Fold10: mtry=76
## - Fold10: mtry=76
## + Fold11: mtry= 2
## - Fold11: mtry= 2
## + Fold11: mtry= 4
## - Fold11: mtry= 4
## + Fold11: mtry= 6
## - Fold11: mtry= 6
## + Fold11: mtry= 8
## - Fold11: mtry= 8
## + Fold11: mtry=10
## - Fold11: mtry=10
## + Fold11: mtry=12
## - Fold11: mtry=12
## + Fold11: mtry=14
## - Fold11: mtry=14
## + Fold11: mtry=16
## - Fold11: mtry=16
## + Fold11: mtry=18
## - Fold11: mtry=18
## + Fold11: mtry=20
## - Fold11: mtry=20
## + Fold11: mtry=22
## - Fold11: mtry=22
## + Fold11: mtry=24
## - Fold11: mtry=24
## + Fold11: mtry=26
## - Fold11: mtry=26
## + Fold11: mtry=28
## - Fold11: mtry=28
## + Fold11: mtry=30
## - Fold11: mtry=30
## + Fold11: mtry=32
## - Fold11: mtry=32
## + Fold11: mtry=34
## - Fold11: mtry=34
## + Fold11: mtry=36
## - Fold11: mtry=36
## + Fold11: mtry=38
## - Fold11: mtry=38
## + Fold11: mtry=40
## - Fold11: mtry=40
## + Fold11: mtry=42
## - Fold11: mtry=42
## + Fold11: mtry=44
## - Fold11: mtry=44
## + Fold11: mtry=46
## - Fold11: mtry=46
## + Fold11: mtry=48
## - Fold11: mtry=48
## + Fold11: mtry=50
## - Fold11: mtry=50
## + Fold11: mtry=52
## - Fold11: mtry=52
## + Fold11: mtry=54
## - Fold11: mtry=54
## + Fold11: mtry=56
## - Fold11: mtry=56
## + Fold11: mtry=58
## - Fold11: mtry=58
## + Fold11: mtry=60
## - Fold11: mtry=60
## + Fold11: mtry=62
## - Fold11: mtry=62
## + Fold11: mtry=64
## - Fold11: mtry=64
## + Fold11: mtry=66
## - Fold11: mtry=66
## + Fold11: mtry=68
## - Fold11: mtry=68
## + Fold11: mtry=70
## - Fold11: mtry=70
## + Fold11: mtry=72
## - Fold11: mtry=72
## + Fold11: mtry=74
## - Fold11: mtry=74
## + Fold11: mtry=76
## - Fold11: mtry=76
## + Fold12: mtry= 2
## - Fold12: mtry= 2
## + Fold12: mtry= 4
## - Fold12: mtry= 4
## + Fold12: mtry= 6
## - Fold12: mtry= 6
## + Fold12: mtry= 8
## - Fold12: mtry= 8
## + Fold12: mtry=10
## - Fold12: mtry=10
## + Fold12: mtry=12
## - Fold12: mtry=12
## + Fold12: mtry=14
## - Fold12: mtry=14
## + Fold12: mtry=16
## - Fold12: mtry=16
## + Fold12: mtry=18
## - Fold12: mtry=18
## + Fold12: mtry=20
## - Fold12: mtry=20
## + Fold12: mtry=22
## - Fold12: mtry=22
## + Fold12: mtry=24
## - Fold12: mtry=24
## + Fold12: mtry=26
## - Fold12: mtry=26
## + Fold12: mtry=28
## - Fold12: mtry=28
## + Fold12: mtry=30
## - Fold12: mtry=30
## + Fold12: mtry=32
## - Fold12: mtry=32
## + Fold12: mtry=34
## - Fold12: mtry=34
## + Fold12: mtry=36
## - Fold12: mtry=36
## + Fold12: mtry=38
## - Fold12: mtry=38
## + Fold12: mtry=40
## - Fold12: mtry=40
## + Fold12: mtry=42
## - Fold12: mtry=42
## + Fold12: mtry=44
## - Fold12: mtry=44
## + Fold12: mtry=46
## - Fold12: mtry=46
## + Fold12: mtry=48
## - Fold12: mtry=48
## + Fold12: mtry=50
## - Fold12: mtry=50
## + Fold12: mtry=52
## - Fold12: mtry=52
## + Fold12: mtry=54
## - Fold12: mtry=54
## + Fold12: mtry=56
## - Fold12: mtry=56
## + Fold12: mtry=58
## - Fold12: mtry=58
## + Fold12: mtry=60
## - Fold12: mtry=60
## + Fold12: mtry=62
## - Fold12: mtry=62
## + Fold12: mtry=64
## - Fold12: mtry=64
## + Fold12: mtry=66
## - Fold12: mtry=66
## + Fold12: mtry=68
## - Fold12: mtry=68
## + Fold12: mtry=70
## - Fold12: mtry=70
## + Fold12: mtry=72
## - Fold12: mtry=72
## + Fold12: mtry=74
## - Fold12: mtry=74
## + Fold12: mtry=76
## - Fold12: mtry=76
## + Fold13: mtry= 2
## - Fold13: mtry= 2
## + Fold13: mtry= 4
## - Fold13: mtry= 4
## + Fold13: mtry= 6
## - Fold13: mtry= 6
## + Fold13: mtry= 8
## - Fold13: mtry= 8
## + Fold13: mtry=10
## - Fold13: mtry=10
## + Fold13: mtry=12
## - Fold13: mtry=12
## + Fold13: mtry=14
## - Fold13: mtry=14
## + Fold13: mtry=16
## - Fold13: mtry=16
## + Fold13: mtry=18
## - Fold13: mtry=18
## + Fold13: mtry=20
## - Fold13: mtry=20
## + Fold13: mtry=22
## - Fold13: mtry=22
## + Fold13: mtry=24
## - Fold13: mtry=24
## + Fold13: mtry=26
## - Fold13: mtry=26
## + Fold13: mtry=28
## - Fold13: mtry=28
## + Fold13: mtry=30
## - Fold13: mtry=30
## + Fold13: mtry=32
## - Fold13: mtry=32
## + Fold13: mtry=34
## - Fold13: mtry=34
## + Fold13: mtry=36
## - Fold13: mtry=36
## + Fold13: mtry=38
## - Fold13: mtry=38
## + Fold13: mtry=40
## - Fold13: mtry=40
## + Fold13: mtry=42
## - Fold13: mtry=42
## + Fold13: mtry=44
## - Fold13: mtry=44
## + Fold13: mtry=46
## - Fold13: mtry=46
## + Fold13: mtry=48
## - Fold13: mtry=48
## + Fold13: mtry=50
## - Fold13: mtry=50
## + Fold13: mtry=52
## - Fold13: mtry=52
## + Fold13: mtry=54
## - Fold13: mtry=54
## + Fold13: mtry=56
## - Fold13: mtry=56
## + Fold13: mtry=58
## - Fold13: mtry=58
## + Fold13: mtry=60
## - Fold13: mtry=60
## + Fold13: mtry=62
## - Fold13: mtry=62
## + Fold13: mtry=64
## - Fold13: mtry=64
## + Fold13: mtry=66
## - Fold13: mtry=66
## + Fold13: mtry=68
## - Fold13: mtry=68
## + Fold13: mtry=70
## - Fold13: mtry=70
## + Fold13: mtry=72
## - Fold13: mtry=72
## + Fold13: mtry=74
## - Fold13: mtry=74
## + Fold13: mtry=76
## - Fold13: mtry=76
## + Fold14: mtry= 2
## - Fold14: mtry= 2
## + Fold14: mtry= 4
## - Fold14: mtry= 4
## + Fold14: mtry= 6
## - Fold14: mtry= 6
## + Fold14: mtry= 8
## - Fold14: mtry= 8
## + Fold14: mtry=10
## - Fold14: mtry=10
## + Fold14: mtry=12
## - Fold14: mtry=12
## + Fold14: mtry=14
## - Fold14: mtry=14
## + Fold14: mtry=16
## - Fold14: mtry=16
## + Fold14: mtry=18
## - Fold14: mtry=18
## + Fold14: mtry=20
## - Fold14: mtry=20
## + Fold14: mtry=22
## - Fold14: mtry=22
## + Fold14: mtry=24
## - Fold14: mtry=24
## + Fold14: mtry=26
## - Fold14: mtry=26
## + Fold14: mtry=28
## - Fold14: mtry=28
## + Fold14: mtry=30
## - Fold14: mtry=30
## + Fold14: mtry=32
## - Fold14: mtry=32
## + Fold14: mtry=34
## - Fold14: mtry=34
## + Fold14: mtry=36
## - Fold14: mtry=36
## + Fold14: mtry=38
## - Fold14: mtry=38
## + Fold14: mtry=40
## - Fold14: mtry=40
## + Fold14: mtry=42
## - Fold14: mtry=42
## + Fold14: mtry=44
## - Fold14: mtry=44
## + Fold14: mtry=46
## - Fold14: mtry=46
## + Fold14: mtry=48
## - Fold14: mtry=48
## + Fold14: mtry=50
## - Fold14: mtry=50
## + Fold14: mtry=52
## - Fold14: mtry=52
## + Fold14: mtry=54
## - Fold14: mtry=54
## + Fold14: mtry=56
## - Fold14: mtry=56
## + Fold14: mtry=58
## - Fold14: mtry=58
## + Fold14: mtry=60
## - Fold14: mtry=60
## + Fold14: mtry=62
## - Fold14: mtry=62
## + Fold14: mtry=64
## - Fold14: mtry=64
## + Fold14: mtry=66
## - Fold14: mtry=66
## + Fold14: mtry=68
## - Fold14: mtry=68
## + Fold14: mtry=70
## - Fold14: mtry=70
## + Fold14: mtry=72
## - Fold14: mtry=72
## + Fold14: mtry=74
## - Fold14: mtry=74
## + Fold14: mtry=76
## - Fold14: mtry=76
## + Fold15: mtry= 2
## - Fold15: mtry= 2
## + Fold15: mtry= 4
## - Fold15: mtry= 4
## + Fold15: mtry= 6
## - Fold15: mtry= 6
## + Fold15: mtry= 8
## - Fold15: mtry= 8
## + Fold15: mtry=10
## - Fold15: mtry=10
## + Fold15: mtry=12
## - Fold15: mtry=12
## + Fold15: mtry=14
## - Fold15: mtry=14
## + Fold15: mtry=16
## - Fold15: mtry=16
## + Fold15: mtry=18
## - Fold15: mtry=18
## + Fold15: mtry=20
## - Fold15: mtry=20
## + Fold15: mtry=22
## - Fold15: mtry=22
## + Fold15: mtry=24
## - Fold15: mtry=24
## + Fold15: mtry=26
## - Fold15: mtry=26
## + Fold15: mtry=28
## - Fold15: mtry=28
## + Fold15: mtry=30
## - Fold15: mtry=30
## + Fold15: mtry=32
## - Fold15: mtry=32
## + Fold15: mtry=34
## - Fold15: mtry=34
## + Fold15: mtry=36
## - Fold15: mtry=36
## + Fold15: mtry=38
## - Fold15: mtry=38
## + Fold15: mtry=40
## - Fold15: mtry=40
## + Fold15: mtry=42
## - Fold15: mtry=42
## + Fold15: mtry=44
## - Fold15: mtry=44
## + Fold15: mtry=46
## - Fold15: mtry=46
## + Fold15: mtry=48
## - Fold15: mtry=48
## + Fold15: mtry=50
## - Fold15: mtry=50
## + Fold15: mtry=52
## - Fold15: mtry=52
## + Fold15: mtry=54
## - Fold15: mtry=54
## + Fold15: mtry=56
## - Fold15: mtry=56
## + Fold15: mtry=58
## - Fold15: mtry=58
## + Fold15: mtry=60
## - Fold15: mtry=60
## + Fold15: mtry=62
## - Fold15: mtry=62
## + Fold15: mtry=64
## - Fold15: mtry=64
## + Fold15: mtry=66
## - Fold15: mtry=66
## + Fold15: mtry=68
## - Fold15: mtry=68
## + Fold15: mtry=70
## - Fold15: mtry=70
## + Fold15: mtry=72
## - Fold15: mtry=72
## + Fold15: mtry=74
## - Fold15: mtry=74
## + Fold15: mtry=76
## - Fold15: mtry=76
## + Fold16: mtry= 2
## - Fold16: mtry= 2
## + Fold16: mtry= 4
## - Fold16: mtry= 4
## + Fold16: mtry= 6
## - Fold16: mtry= 6
## + Fold16: mtry= 8
## - Fold16: mtry= 8
## + Fold16: mtry=10
## - Fold16: mtry=10
## + Fold16: mtry=12
## - Fold16: mtry=12
## + Fold16: mtry=14
## - Fold16: mtry=14
## + Fold16: mtry=16
## - Fold16: mtry=16
## + Fold16: mtry=18
## - Fold16: mtry=18
## + Fold16: mtry=20
## - Fold16: mtry=20
## + Fold16: mtry=22
## - Fold16: mtry=22
## + Fold16: mtry=24
## - Fold16: mtry=24
## + Fold16: mtry=26
## - Fold16: mtry=26
## + Fold16: mtry=28
## - Fold16: mtry=28
## + Fold16: mtry=30
## - Fold16: mtry=30
## + Fold16: mtry=32
## - Fold16: mtry=32
## + Fold16: mtry=34
## - Fold16: mtry=34
## + Fold16: mtry=36
## - Fold16: mtry=36
## + Fold16: mtry=38
## - Fold16: mtry=38
## + Fold16: mtry=40
## - Fold16: mtry=40
## + Fold16: mtry=42
## - Fold16: mtry=42
## + Fold16: mtry=44
## - Fold16: mtry=44
## + Fold16: mtry=46
## - Fold16: mtry=46
## + Fold16: mtry=48
## - Fold16: mtry=48
## + Fold16: mtry=50
## - Fold16: mtry=50
## + Fold16: mtry=52
## - Fold16: mtry=52
## + Fold16: mtry=54
## - Fold16: mtry=54
## + Fold16: mtry=56
## - Fold16: mtry=56
## + Fold16: mtry=58
## - Fold16: mtry=58
## + Fold16: mtry=60
## - Fold16: mtry=60
## + Fold16: mtry=62
## - Fold16: mtry=62
## + Fold16: mtry=64
## - Fold16: mtry=64
## + Fold16: mtry=66
## - Fold16: mtry=66
## + Fold16: mtry=68
## - Fold16: mtry=68
## + Fold16: mtry=70
## - Fold16: mtry=70
## + Fold16: mtry=72
## - Fold16: mtry=72
## + Fold16: mtry=74
## - Fold16: mtry=74
## + Fold16: mtry=76
## - Fold16: mtry=76
## + Fold17: mtry= 2
## - Fold17: mtry= 2
## + Fold17: mtry= 4
## - Fold17: mtry= 4
## + Fold17: mtry= 6
## - Fold17: mtry= 6
## + Fold17: mtry= 8
## - Fold17: mtry= 8
## + Fold17: mtry=10
## - Fold17: mtry=10
## + Fold17: mtry=12
## - Fold17: mtry=12
## + Fold17: mtry=14
## - Fold17: mtry=14
## + Fold17: mtry=16
## - Fold17: mtry=16
## + Fold17: mtry=18
## - Fold17: mtry=18
## + Fold17: mtry=20
## - Fold17: mtry=20
## + Fold17: mtry=22
## - Fold17: mtry=22
## + Fold17: mtry=24
## - Fold17: mtry=24
## + Fold17: mtry=26
## - Fold17: mtry=26
## + Fold17: mtry=28
## - Fold17: mtry=28
## + Fold17: mtry=30
## - Fold17: mtry=30
## + Fold17: mtry=32
## - Fold17: mtry=32
## + Fold17: mtry=34
## - Fold17: mtry=34
## + Fold17: mtry=36
## - Fold17: mtry=36
## + Fold17: mtry=38
## - Fold17: mtry=38
## + Fold17: mtry=40
## - Fold17: mtry=40
## + Fold17: mtry=42
## - Fold17: mtry=42
## + Fold17: mtry=44
## - Fold17: mtry=44
## + Fold17: mtry=46
## - Fold17: mtry=46
## + Fold17: mtry=48
## - Fold17: mtry=48
## + Fold17: mtry=50
## - Fold17: mtry=50
## + Fold17: mtry=52
## - Fold17: mtry=52
## + Fold17: mtry=54
## - Fold17: mtry=54
## + Fold17: mtry=56
## - Fold17: mtry=56
## + Fold17: mtry=58
## - Fold17: mtry=58
## + Fold17: mtry=60
## - Fold17: mtry=60
## + Fold17: mtry=62
## - Fold17: mtry=62
## + Fold17: mtry=64
## - Fold17: mtry=64
## + Fold17: mtry=66
## - Fold17: mtry=66
## + Fold17: mtry=68
## - Fold17: mtry=68
## + Fold17: mtry=70
## - Fold17: mtry=70
## + Fold17: mtry=72
## - Fold17: mtry=72
## + Fold17: mtry=74
## - Fold17: mtry=74
## + Fold17: mtry=76
## - Fold17: mtry=76
## + Fold18: mtry= 2
## - Fold18: mtry= 2
## + Fold18: mtry= 4
## - Fold18: mtry= 4
## + Fold18: mtry= 6
## - Fold18: mtry= 6
## + Fold18: mtry= 8
## - Fold18: mtry= 8
## + Fold18: mtry=10
## - Fold18: mtry=10
## + Fold18: mtry=12
## - Fold18: mtry=12
## + Fold18: mtry=14
## - Fold18: mtry=14
## + Fold18: mtry=16
## - Fold18: mtry=16
## + Fold18: mtry=18
## - Fold18: mtry=18
## + Fold18: mtry=20
## - Fold18: mtry=20
## + Fold18: mtry=22
## - Fold18: mtry=22
## + Fold18: mtry=24
## - Fold18: mtry=24
## + Fold18: mtry=26
## - Fold18: mtry=26
## + Fold18: mtry=28
## - Fold18: mtry=28
## + Fold18: mtry=30
## - Fold18: mtry=30
## + Fold18: mtry=32
## - Fold18: mtry=32
## + Fold18: mtry=34
## - Fold18: mtry=34
## + Fold18: mtry=36
## - Fold18: mtry=36
## + Fold18: mtry=38
## - Fold18: mtry=38
## + Fold18: mtry=40
## - Fold18: mtry=40
## + Fold18: mtry=42
## - Fold18: mtry=42
## + Fold18: mtry=44
## - Fold18: mtry=44
## + Fold18: mtry=46
## - Fold18: mtry=46
## + Fold18: mtry=48
## - Fold18: mtry=48
## + Fold18: mtry=50
## - Fold18: mtry=50
## + Fold18: mtry=52
## - Fold18: mtry=52
## + Fold18: mtry=54
## - Fold18: mtry=54
## + Fold18: mtry=56
## - Fold18: mtry=56
## + Fold18: mtry=58
## - Fold18: mtry=58
## + Fold18: mtry=60
## - Fold18: mtry=60
## + Fold18: mtry=62
## - Fold18: mtry=62
## + Fold18: mtry=64
## - Fold18: mtry=64
## + Fold18: mtry=66
## - Fold18: mtry=66
## + Fold18: mtry=68
## - Fold18: mtry=68
## + Fold18: mtry=70
## - Fold18: mtry=70
## + Fold18: mtry=72
## - Fold18: mtry=72
## + Fold18: mtry=74
## - Fold18: mtry=74
## + Fold18: mtry=76
## - Fold18: mtry=76
## + Fold19: mtry= 2
## - Fold19: mtry= 2
## + Fold19: mtry= 4
## - Fold19: mtry= 4
## + Fold19: mtry= 6
## - Fold19: mtry= 6
## + Fold19: mtry= 8
## - Fold19: mtry= 8
## + Fold19: mtry=10
## - Fold19: mtry=10
## + Fold19: mtry=12
## - Fold19: mtry=12
## + Fold19: mtry=14
## - Fold19: mtry=14
## + Fold19: mtry=16
## - Fold19: mtry=16
## + Fold19: mtry=18
## - Fold19: mtry=18
## + Fold19: mtry=20
## - Fold19: mtry=20
## + Fold19: mtry=22
## - Fold19: mtry=22
## + Fold19: mtry=24
## - Fold19: mtry=24
## + Fold19: mtry=26
## - Fold19: mtry=26
## + Fold19: mtry=28
## - Fold19: mtry=28
## + Fold19: mtry=30
## - Fold19: mtry=30
## + Fold19: mtry=32
## - Fold19: mtry=32
## + Fold19: mtry=34
## - Fold19: mtry=34
## + Fold19: mtry=36
## - Fold19: mtry=36
## + Fold19: mtry=38
## - Fold19: mtry=38
## + Fold19: mtry=40
## - Fold19: mtry=40
## + Fold19: mtry=42
## - Fold19: mtry=42
## + Fold19: mtry=44
## - Fold19: mtry=44
## + Fold19: mtry=46
## - Fold19: mtry=46
## + Fold19: mtry=48
## - Fold19: mtry=48
## + Fold19: mtry=50
## - Fold19: mtry=50
## + Fold19: mtry=52
## - Fold19: mtry=52
## + Fold19: mtry=54
## - Fold19: mtry=54
## + Fold19: mtry=56
## - Fold19: mtry=56
## + Fold19: mtry=58
## - Fold19: mtry=58
## + Fold19: mtry=60
## - Fold19: mtry=60
## + Fold19: mtry=62
## - Fold19: mtry=62
## + Fold19: mtry=64
## - Fold19: mtry=64
## + Fold19: mtry=66
## - Fold19: mtry=66
## + Fold19: mtry=68
## - Fold19: mtry=68
## + Fold19: mtry=70
## - Fold19: mtry=70
## + Fold19: mtry=72
## - Fold19: mtry=72
## + Fold19: mtry=74
## - Fold19: mtry=74
## + Fold19: mtry=76
## - Fold19: mtry=76
## + Fold20: mtry= 2
## - Fold20: mtry= 2
## + Fold20: mtry= 4
## - Fold20: mtry= 4
## + Fold20: mtry= 6
## - Fold20: mtry= 6
## + Fold20: mtry= 8
## - Fold20: mtry= 8
## + Fold20: mtry=10
## - Fold20: mtry=10
## + Fold20: mtry=12
## - Fold20: mtry=12
## + Fold20: mtry=14
## - Fold20: mtry=14
## + Fold20: mtry=16
## - Fold20: mtry=16
## + Fold20: mtry=18
## - Fold20: mtry=18
## + Fold20: mtry=20
## - Fold20: mtry=20
## + Fold20: mtry=22
## - Fold20: mtry=22
## + Fold20: mtry=24
## - Fold20: mtry=24
## + Fold20: mtry=26
## - Fold20: mtry=26
## + Fold20: mtry=28
## - Fold20: mtry=28
## + Fold20: mtry=30
## - Fold20: mtry=30
## + Fold20: mtry=32
## - Fold20: mtry=32
## + Fold20: mtry=34
## - Fold20: mtry=34
## + Fold20: mtry=36
## - Fold20: mtry=36
## + Fold20: mtry=38
## - Fold20: mtry=38
## + Fold20: mtry=40
## - Fold20: mtry=40
## + Fold20: mtry=42
## - Fold20: mtry=42
## + Fold20: mtry=44
## - Fold20: mtry=44
## + Fold20: mtry=46
## - Fold20: mtry=46
## + Fold20: mtry=48
## - Fold20: mtry=48
## + Fold20: mtry=50
## - Fold20: mtry=50
## + Fold20: mtry=52
## - Fold20: mtry=52
## + Fold20: mtry=54
## - Fold20: mtry=54
## + Fold20: mtry=56
## - Fold20: mtry=56
## + Fold20: mtry=58
## - Fold20: mtry=58
## + Fold20: mtry=60
## - Fold20: mtry=60
## + Fold20: mtry=62
## - Fold20: mtry=62
## + Fold20: mtry=64
## - Fold20: mtry=64
## + Fold20: mtry=66
## - Fold20: mtry=66
## + Fold20: mtry=68
## - Fold20: mtry=68
## + Fold20: mtry=70
## - Fold20: mtry=70
## + Fold20: mtry=72
## - Fold20: mtry=72
## + Fold20: mtry=74
## - Fold20: mtry=74
## + Fold20: mtry=76
## - Fold20: mtry=76
## + Fold21: mtry= 2
## - Fold21: mtry= 2
## + Fold21: mtry= 4
## - Fold21: mtry= 4
## + Fold21: mtry= 6
## - Fold21: mtry= 6
## + Fold21: mtry= 8
## - Fold21: mtry= 8
## + Fold21: mtry=10
## - Fold21: mtry=10
## + Fold21: mtry=12
## - Fold21: mtry=12
## + Fold21: mtry=14
## - Fold21: mtry=14
## + Fold21: mtry=16
## - Fold21: mtry=16
## + Fold21: mtry=18
## - Fold21: mtry=18
## + Fold21: mtry=20
## - Fold21: mtry=20
## + Fold21: mtry=22
## - Fold21: mtry=22
## + Fold21: mtry=24
## - Fold21: mtry=24
## + Fold21: mtry=26
## - Fold21: mtry=26
## + Fold21: mtry=28
## - Fold21: mtry=28
## + Fold21: mtry=30
## - Fold21: mtry=30
## + Fold21: mtry=32
## - Fold21: mtry=32
## + Fold21: mtry=34
## - Fold21: mtry=34
## + Fold21: mtry=36
## - Fold21: mtry=36
## + Fold21: mtry=38
## - Fold21: mtry=38
## + Fold21: mtry=40
## - Fold21: mtry=40
## + Fold21: mtry=42
## - Fold21: mtry=42
## + Fold21: mtry=44
## - Fold21: mtry=44
## + Fold21: mtry=46
## - Fold21: mtry=46
## + Fold21: mtry=48
## - Fold21: mtry=48
## + Fold21: mtry=50
## - Fold21: mtry=50
## + Fold21: mtry=52
## - Fold21: mtry=52
## + Fold21: mtry=54
## - Fold21: mtry=54
## + Fold21: mtry=56
## - Fold21: mtry=56
## + Fold21: mtry=58
## - Fold21: mtry=58
## + Fold21: mtry=60
## - Fold21: mtry=60
## + Fold21: mtry=62
## - Fold21: mtry=62
## + Fold21: mtry=64
## - Fold21: mtry=64
## + Fold21: mtry=66
## - Fold21: mtry=66
## + Fold21: mtry=68
## - Fold21: mtry=68
## + Fold21: mtry=70
## - Fold21: mtry=70
## + Fold21: mtry=72
## - Fold21: mtry=72
## + Fold21: mtry=74
## - Fold21: mtry=74
## + Fold21: mtry=76
## - Fold21: mtry=76
## + Fold22: mtry= 2
## - Fold22: mtry= 2
## + Fold22: mtry= 4
## - Fold22: mtry= 4
## + Fold22: mtry= 6
## - Fold22: mtry= 6
## + Fold22: mtry= 8
## - Fold22: mtry= 8
## + Fold22: mtry=10
## - Fold22: mtry=10
## + Fold22: mtry=12
## - Fold22: mtry=12
## + Fold22: mtry=14
## - Fold22: mtry=14
## + Fold22: mtry=16
## - Fold22: mtry=16
## + Fold22: mtry=18
## - Fold22: mtry=18
## + Fold22: mtry=20
## - Fold22: mtry=20
## + Fold22: mtry=22
## - Fold22: mtry=22
## + Fold22: mtry=24
## - Fold22: mtry=24
## + Fold22: mtry=26
## - Fold22: mtry=26
## + Fold22: mtry=28
## - Fold22: mtry=28
## + Fold22: mtry=30
## - Fold22: mtry=30
## + Fold22: mtry=32
## - Fold22: mtry=32
## + Fold22: mtry=34
## - Fold22: mtry=34
## + Fold22: mtry=36
## - Fold22: mtry=36
## + Fold22: mtry=38
## - Fold22: mtry=38
## + Fold22: mtry=40
## - Fold22: mtry=40
## + Fold22: mtry=42
## - Fold22: mtry=42
## + Fold22: mtry=44
## - Fold22: mtry=44
## + Fold22: mtry=46
## - Fold22: mtry=46
## + Fold22: mtry=48
## - Fold22: mtry=48
## + Fold22: mtry=50
## - Fold22: mtry=50
## + Fold22: mtry=52
## - Fold22: mtry=52
## + Fold22: mtry=54
## - Fold22: mtry=54
## + Fold22: mtry=56
## - Fold22: mtry=56
## + Fold22: mtry=58
## - Fold22: mtry=58
## + Fold22: mtry=60
## - Fold22: mtry=60
## + Fold22: mtry=62
## - Fold22: mtry=62
## + Fold22: mtry=64
## - Fold22: mtry=64
## + Fold22: mtry=66
## - Fold22: mtry=66
## + Fold22: mtry=68
## - Fold22: mtry=68
## + Fold22: mtry=70
## - Fold22: mtry=70
## + Fold22: mtry=72
## - Fold22: mtry=72
## + Fold22: mtry=74
## - Fold22: mtry=74
## + Fold22: mtry=76
## - Fold22: mtry=76
## + Fold23: mtry= 2
## - Fold23: mtry= 2
## + Fold23: mtry= 4
## - Fold23: mtry= 4
## + Fold23: mtry= 6
## - Fold23: mtry= 6
## + Fold23: mtry= 8
## - Fold23: mtry= 8
## + Fold23: mtry=10
## - Fold23: mtry=10
## + Fold23: mtry=12
## - Fold23: mtry=12
## + Fold23: mtry=14
## - Fold23: mtry=14
## + Fold23: mtry=16
## - Fold23: mtry=16
## + Fold23: mtry=18
## - Fold23: mtry=18
## + Fold23: mtry=20
## - Fold23: mtry=20
## + Fold23: mtry=22
## - Fold23: mtry=22
## + Fold23: mtry=24
## - Fold23: mtry=24
## + Fold23: mtry=26
## - Fold23: mtry=26
## + Fold23: mtry=28
## - Fold23: mtry=28
## + Fold23: mtry=30
## - Fold23: mtry=30
## + Fold23: mtry=32
## - Fold23: mtry=32
## + Fold23: mtry=34
## - Fold23: mtry=34
## + Fold23: mtry=36
## - Fold23: mtry=36
## + Fold23: mtry=38
## - Fold23: mtry=38
## + Fold23: mtry=40
## - Fold23: mtry=40
## + Fold23: mtry=42
## - Fold23: mtry=42
## + Fold23: mtry=44
## - Fold23: mtry=44
## + Fold23: mtry=46
## - Fold23: mtry=46
## + Fold23: mtry=48
## - Fold23: mtry=48
## + Fold23: mtry=50
## - Fold23: mtry=50
## + Fold23: mtry=52
## - Fold23: mtry=52
## + Fold23: mtry=54
## - Fold23: mtry=54
## + Fold23: mtry=56
## - Fold23: mtry=56
## + Fold23: mtry=58
## - Fold23: mtry=58
## + Fold23: mtry=60
## - Fold23: mtry=60
## + Fold23: mtry=62
## - Fold23: mtry=62
## + Fold23: mtry=64
## - Fold23: mtry=64
## + Fold23: mtry=66
## - Fold23: mtry=66
## + Fold23: mtry=68
## - Fold23: mtry=68
## + Fold23: mtry=70
## - Fold23: mtry=70
## + Fold23: mtry=72
## - Fold23: mtry=72
## + Fold23: mtry=74
## - Fold23: mtry=74
## + Fold23: mtry=76
## - Fold23: mtry=76
## + Fold24: mtry= 2
## - Fold24: mtry= 2
## + Fold24: mtry= 4
## - Fold24: mtry= 4
## + Fold24: mtry= 6
## - Fold24: mtry= 6
## + Fold24: mtry= 8
## - Fold24: mtry= 8
## + Fold24: mtry=10
## - Fold24: mtry=10
## + Fold24: mtry=12
## - Fold24: mtry=12
## + Fold24: mtry=14
## - Fold24: mtry=14
## + Fold24: mtry=16
## - Fold24: mtry=16
## + Fold24: mtry=18
## - Fold24: mtry=18
## + Fold24: mtry=20
## - Fold24: mtry=20
## + Fold24: mtry=22
## - Fold24: mtry=22
## + Fold24: mtry=24
## - Fold24: mtry=24
## + Fold24: mtry=26
## - Fold24: mtry=26
## + Fold24: mtry=28
## - Fold24: mtry=28
## + Fold24: mtry=30
## - Fold24: mtry=30
## + Fold24: mtry=32
## - Fold24: mtry=32
## + Fold24: mtry=34
## - Fold24: mtry=34
## + Fold24: mtry=36
## - Fold24: mtry=36
## + Fold24: mtry=38
## - Fold24: mtry=38
## + Fold24: mtry=40
## - Fold24: mtry=40
## + Fold24: mtry=42
## - Fold24: mtry=42
## + Fold24: mtry=44
## - Fold24: mtry=44
## + Fold24: mtry=46
## - Fold24: mtry=46
## + Fold24: mtry=48
## - Fold24: mtry=48
## + Fold24: mtry=50
## - Fold24: mtry=50
## + Fold24: mtry=52
## - Fold24: mtry=52
## + Fold24: mtry=54
## - Fold24: mtry=54
## + Fold24: mtry=56
## - Fold24: mtry=56
## + Fold24: mtry=58
## - Fold24: mtry=58
## + Fold24: mtry=60
## - Fold24: mtry=60
## + Fold24: mtry=62
## - Fold24: mtry=62
## + Fold24: mtry=64
## - Fold24: mtry=64
## + Fold24: mtry=66
## - Fold24: mtry=66
## + Fold24: mtry=68
## - Fold24: mtry=68
## + Fold24: mtry=70
## - Fold24: mtry=70
## + Fold24: mtry=72
## - Fold24: mtry=72
## + Fold24: mtry=74
## - Fold24: mtry=74
## + Fold24: mtry=76
## - Fold24: mtry=76
## + Fold25: mtry= 2
## - Fold25: mtry= 2
## + Fold25: mtry= 4
## - Fold25: mtry= 4
## + Fold25: mtry= 6
## - Fold25: mtry= 6
## + Fold25: mtry= 8
## - Fold25: mtry= 8
## + Fold25: mtry=10
## - Fold25: mtry=10
## + Fold25: mtry=12
## - Fold25: mtry=12
## + Fold25: mtry=14
## - Fold25: mtry=14
## + Fold25: mtry=16
## - Fold25: mtry=16
## + Fold25: mtry=18
## - Fold25: mtry=18
## + Fold25: mtry=20
## - Fold25: mtry=20
## + Fold25: mtry=22
## - Fold25: mtry=22
## + Fold25: mtry=24
## - Fold25: mtry=24
## + Fold25: mtry=26
## - Fold25: mtry=26
## + Fold25: mtry=28
## - Fold25: mtry=28
## + Fold25: mtry=30
## - Fold25: mtry=30
## + Fold25: mtry=32
## - Fold25: mtry=32
## + Fold25: mtry=34
## - Fold25: mtry=34
## + Fold25: mtry=36
## - Fold25: mtry=36
## + Fold25: mtry=38
## - Fold25: mtry=38
## + Fold25: mtry=40
## - Fold25: mtry=40
## + Fold25: mtry=42
## - Fold25: mtry=42
## + Fold25: mtry=44
## - Fold25: mtry=44
## + Fold25: mtry=46
## - Fold25: mtry=46
## + Fold25: mtry=48
## - Fold25: mtry=48
## + Fold25: mtry=50
## - Fold25: mtry=50
## + Fold25: mtry=52
## - Fold25: mtry=52
## + Fold25: mtry=54
## - Fold25: mtry=54
## + Fold25: mtry=56
## - Fold25: mtry=56
## + Fold25: mtry=58
## - Fold25: mtry=58
## + Fold25: mtry=60
## - Fold25: mtry=60
## + Fold25: mtry=62
## - Fold25: mtry=62
## + Fold25: mtry=64
## - Fold25: mtry=64
## + Fold25: mtry=66
## - Fold25: mtry=66
## + Fold25: mtry=68
## - Fold25: mtry=68
## + Fold25: mtry=70
## - Fold25: mtry=70
## + Fold25: mtry=72
## - Fold25: mtry=72
## + Fold25: mtry=74
## - Fold25: mtry=74
## + Fold25: mtry=76
## - Fold25: mtry=76
## + Fold26: mtry= 2
## - Fold26: mtry= 2
## + Fold26: mtry= 4
## - Fold26: mtry= 4
## + Fold26: mtry= 6
## - Fold26: mtry= 6
## + Fold26: mtry= 8
## - Fold26: mtry= 8
## + Fold26: mtry=10
## - Fold26: mtry=10
## + Fold26: mtry=12
## - Fold26: mtry=12
## + Fold26: mtry=14
## - Fold26: mtry=14
## + Fold26: mtry=16
## - Fold26: mtry=16
## + Fold26: mtry=18
## - Fold26: mtry=18
## + Fold26: mtry=20
## - Fold26: mtry=20
## + Fold26: mtry=22
## - Fold26: mtry=22
## + Fold26: mtry=24
## - Fold26: mtry=24
## + Fold26: mtry=26
## - Fold26: mtry=26
## + Fold26: mtry=28
## - Fold26: mtry=28
## + Fold26: mtry=30
## - Fold26: mtry=30
## + Fold26: mtry=32
## - Fold26: mtry=32
## + Fold26: mtry=34
## - Fold26: mtry=34
## + Fold26: mtry=36
## - Fold26: mtry=36
## + Fold26: mtry=38
## - Fold26: mtry=38
## + Fold26: mtry=40
## - Fold26: mtry=40
## + Fold26: mtry=42
## - Fold26: mtry=42
## + Fold26: mtry=44
## - Fold26: mtry=44
## + Fold26: mtry=46
## - Fold26: mtry=46
## + Fold26: mtry=48
## - Fold26: mtry=48
## + Fold26: mtry=50
## - Fold26: mtry=50
## + Fold26: mtry=52
## - Fold26: mtry=52
## + Fold26: mtry=54
## - Fold26: mtry=54
## + Fold26: mtry=56
## - Fold26: mtry=56
## + Fold26: mtry=58
## - Fold26: mtry=58
## + Fold26: mtry=60
## - Fold26: mtry=60
## + Fold26: mtry=62
## - Fold26: mtry=62
## + Fold26: mtry=64
## - Fold26: mtry=64
## + Fold26: mtry=66
## - Fold26: mtry=66
## + Fold26: mtry=68
## - Fold26: mtry=68
## + Fold26: mtry=70
## - Fold26: mtry=70
## + Fold26: mtry=72
## - Fold26: mtry=72
## + Fold26: mtry=74
## - Fold26: mtry=74
## + Fold26: mtry=76
## - Fold26: mtry=76
## + Fold27: mtry= 2
## - Fold27: mtry= 2
## + Fold27: mtry= 4
## - Fold27: mtry= 4
## + Fold27: mtry= 6
## - Fold27: mtry= 6
## + Fold27: mtry= 8
## - Fold27: mtry= 8
## + Fold27: mtry=10
## - Fold27: mtry=10
## + Fold27: mtry=12
## - Fold27: mtry=12
## + Fold27: mtry=14
## - Fold27: mtry=14
## + Fold27: mtry=16
## - Fold27: mtry=16
## + Fold27: mtry=18
## - Fold27: mtry=18
## + Fold27: mtry=20
## - Fold27: mtry=20
## + Fold27: mtry=22
## - Fold27: mtry=22
## + Fold27: mtry=24
## - Fold27: mtry=24
## + Fold27: mtry=26
## - Fold27: mtry=26
## + Fold27: mtry=28
## - Fold27: mtry=28
## + Fold27: mtry=30
## - Fold27: mtry=30
## + Fold27: mtry=32
## - Fold27: mtry=32
## + Fold27: mtry=34
## - Fold27: mtry=34
## + Fold27: mtry=36
## - Fold27: mtry=36
## + Fold27: mtry=38
## - Fold27: mtry=38
## + Fold27: mtry=40
## - Fold27: mtry=40
## + Fold27: mtry=42
## - Fold27: mtry=42
## + Fold27: mtry=44
## - Fold27: mtry=44
## + Fold27: mtry=46
## - Fold27: mtry=46
## + Fold27: mtry=48
## - Fold27: mtry=48
## + Fold27: mtry=50
## - Fold27: mtry=50
## + Fold27: mtry=52
## - Fold27: mtry=52
## + Fold27: mtry=54
## - Fold27: mtry=54
## + Fold27: mtry=56
## - Fold27: mtry=56
## + Fold27: mtry=58
## - Fold27: mtry=58
## + Fold27: mtry=60
## - Fold27: mtry=60
## + Fold27: mtry=62
## - Fold27: mtry=62
## + Fold27: mtry=64
## - Fold27: mtry=64
## + Fold27: mtry=66
## - Fold27: mtry=66
## + Fold27: mtry=68
## - Fold27: mtry=68
## + Fold27: mtry=70
## - Fold27: mtry=70
## + Fold27: mtry=72
## - Fold27: mtry=72
## + Fold27: mtry=74
## - Fold27: mtry=74
## + Fold27: mtry=76
## - Fold27: mtry=76
## + Fold28: mtry= 2
## - Fold28: mtry= 2
## + Fold28: mtry= 4
## - Fold28: mtry= 4
## + Fold28: mtry= 6
## - Fold28: mtry= 6
## + Fold28: mtry= 8
## - Fold28: mtry= 8
## + Fold28: mtry=10
## - Fold28: mtry=10
## + Fold28: mtry=12
## - Fold28: mtry=12
## + Fold28: mtry=14
## - Fold28: mtry=14
## + Fold28: mtry=16
## - Fold28: mtry=16
## + Fold28: mtry=18
## - Fold28: mtry=18
## + Fold28: mtry=20
## - Fold28: mtry=20
## + Fold28: mtry=22
## - Fold28: mtry=22
## + Fold28: mtry=24
## - Fold28: mtry=24
## + Fold28: mtry=26
## - Fold28: mtry=26
## + Fold28: mtry=28
## - Fold28: mtry=28
## + Fold28: mtry=30
## - Fold28: mtry=30
## + Fold28: mtry=32
## - Fold28: mtry=32
## + Fold28: mtry=34
## - Fold28: mtry=34
## + Fold28: mtry=36
## - Fold28: mtry=36
## + Fold28: mtry=38
## - Fold28: mtry=38
## + Fold28: mtry=40
## - Fold28: mtry=40
## + Fold28: mtry=42
## - Fold28: mtry=42
## + Fold28: mtry=44
## - Fold28: mtry=44
## + Fold28: mtry=46
## - Fold28: mtry=46
## + Fold28: mtry=48
## - Fold28: mtry=48
## + Fold28: mtry=50
## - Fold28: mtry=50
## + Fold28: mtry=52
## - Fold28: mtry=52
## + Fold28: mtry=54
## - Fold28: mtry=54
## + Fold28: mtry=56
## - Fold28: mtry=56
## + Fold28: mtry=58
## - Fold28: mtry=58
## + Fold28: mtry=60
## - Fold28: mtry=60
## + Fold28: mtry=62
## - Fold28: mtry=62
## + Fold28: mtry=64
## - Fold28: mtry=64
## + Fold28: mtry=66
## - Fold28: mtry=66
## + Fold28: mtry=68
## - Fold28: mtry=68
## + Fold28: mtry=70
## - Fold28: mtry=70
## + Fold28: mtry=72
## - Fold28: mtry=72
## + Fold28: mtry=74
## - Fold28: mtry=74
## + Fold28: mtry=76
## - Fold28: mtry=76
## Aggregating results
## Selecting tuning parameters
## Fitting mtry = 74 on full training set# View results
print(rf_model)## Random Forest
##
## 28 samples
## 77 predictors
##
## Pre-processing: scaled (77), centered (77)
## Resampling: Leave-One-Out Cross-Validation
## Summary of sample sizes: 27, 27, 27, 27, 27, 27, ...
## Resampling results across tuning parameters:
##
## mtry RMSE Rsquared MAE
## 2 0.1340677 0.7027724 0.10611360
## 4 0.1223014 0.7525156 0.09685893
## 6 0.1185285 0.7394641 0.09662985
## 8 0.1131596 0.7621642 0.09156987
## 10 0.1147484 0.7477514 0.09328456
## 12 0.1131942 0.7511312 0.09323591
## 14 0.1113480 0.7590494 0.09089457
## 16 0.1070755 0.7830346 0.08778009
## 18 0.1049438 0.7868920 0.08733542
## 20 0.1088106 0.7573214 0.09182430
## 22 0.1076286 0.7647823 0.08962344
## 24 0.1042948 0.7816854 0.08719319
## 26 0.1063151 0.7688885 0.08880109
## 28 0.1037394 0.7854538 0.08656739
## 30 0.1063075 0.7701789 0.08995771
## 32 0.1047680 0.7739923 0.08822147
## 34 0.1039211 0.7787565 0.08775866
## 36 0.1042549 0.7797645 0.08812937
## 38 0.1036824 0.7820748 0.08713922
## 40 0.1033886 0.7819013 0.08709370
## 42 0.1028162 0.7824084 0.08807994
## 44 0.1037518 0.7781091 0.08836165
## 46 0.1041355 0.7719966 0.08842543
## 48 0.1042260 0.7763559 0.08846454
## 50 0.1044087 0.7721682 0.08833346
## 52 0.1034126 0.7780116 0.08811085
## 54 0.1038088 0.7718965 0.08782083
## 56 0.1043292 0.7721859 0.08976233
## 58 0.1034437 0.7790495 0.08847410
## 60 0.1030409 0.7777514 0.08812578
## 62 0.1037524 0.7750573 0.08962625
## 64 0.1033621 0.7761743 0.08880371
## 66 0.1057159 0.7629484 0.09026237
## 68 0.1034075 0.7752889 0.08807459
## 70 0.1020962 0.7809881 0.08736141
## 72 0.1032705 0.7769025 0.08901812
## 74 0.1018470 0.7834390 0.08764772
## 76 0.1052073 0.7652970 0.09070107
##
## RMSE was used to select the optimal model using the smallest value.
## The final value used for the model was mtry = 74.plot(rf_model) # Plot performance across hyperparameters
varImpPlot(rf_model$finalModel) # Plot variable importance
Gradient boosting
gbm_grid <- expand.grid(
n.trees = c(50, 100, 200), # Fewer trees
interaction.depth = c(1, 2, 3), # Much smaller tree depth
shrinkage = c(0.01, 0.05, 0.1), # Keep these values
n.minobsinnode = c(1, 3, 5) # Smaller minimum observations
)
gbm_model <- train(
mean_trans_docs ~ .,
data = data_aggr,
method = "gbm",
preProc = c('scale', 'center'),
trControl = control,
tuneGrid = gbm_grid)## + Fold01: shrinkage=0.01, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0437 nan 0.0100 0.0006
## 2 0.0434 nan 0.0100 0.0003
## 3 0.0426 nan 0.0100 0.0006
## 4 0.0421 nan 0.0100 0.0005
## 5 0.0416 nan 0.0100 0.0002
## 6 0.0411 nan 0.0100 0.0005
## 7 0.0407 nan 0.0100 0.0001
## 8 0.0403 nan 0.0100 0.0003
## 9 0.0398 nan 0.0100 0.0003
## 10 0.0394 nan 0.0100 0.0005
## 20 0.0350 nan 0.0100 0.0003
## 40 0.0281 nan 0.0100 0.0003
## 60 0.0228 nan 0.0100 0.0002
## 80 0.0185 nan 0.0100 0.0001
## 100 0.0153 nan 0.0100 0.0001
## 120 0.0129 nan 0.0100 0.0001
## 140 0.0109 nan 0.0100 0.0001
## 160 0.0091 nan 0.0100 0.0001
## 180 0.0076 nan 0.0100 0.0001
## 200 0.0065 nan 0.0100 0.0001
##
## - Fold01: shrinkage=0.01, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold01: shrinkage=0.01, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0441 nan 0.0100 -0.0001
## 2 0.0436 nan 0.0100 0.0005
## 3 0.0433 nan 0.0100 0.0003
## 4 0.0427 nan 0.0100 0.0005
## 5 0.0423 nan 0.0100 0.0003
## 6 0.0417 nan 0.0100 0.0003
## 7 0.0411 nan 0.0100 0.0004
## 8 0.0405 nan 0.0100 0.0004
## 9 0.0400 nan 0.0100 -0.0000
## 10 0.0396 nan 0.0100 0.0004
## 20 0.0349 nan 0.0100 0.0003
## 40 0.0276 nan 0.0100 0.0003
## 60 0.0220 nan 0.0100 0.0002
## 80 0.0177 nan 0.0100 0.0002
## 100 0.0143 nan 0.0100 0.0001
## 120 0.0117 nan 0.0100 0.0000
## 140 0.0096 nan 0.0100 0.0000
## 160 0.0080 nan 0.0100 0.0000
## 180 0.0068 nan 0.0100 0.0000
## 200 0.0057 nan 0.0100 0.0000
##
## - Fold01: shrinkage=0.01, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold01: shrinkage=0.01, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0440 nan 0.0100 0.0004
## 2 0.0434 nan 0.0100 0.0006
## 3 0.0429 nan 0.0100 0.0005
## 4 0.0423 nan 0.0100 0.0006
## 5 0.0418 nan 0.0100 0.0005
## 6 0.0413 nan 0.0100 0.0005
## 7 0.0408 nan 0.0100 0.0005
## 8 0.0404 nan 0.0100 0.0005
## 9 0.0401 nan 0.0100 -0.0000
## 10 0.0395 nan 0.0100 0.0006
## 20 0.0352 nan 0.0100 0.0005
## 40 0.0281 nan 0.0100 0.0004
## 60 0.0229 nan 0.0100 0.0002
## 80 0.0192 nan 0.0100 0.0002
## 100 0.0164 nan 0.0100 0.0000
## 120 0.0138 nan 0.0100 0.0001
## 140 0.0120 nan 0.0100 0.0000
## 160 0.0104 nan 0.0100 0.0000
## 180 0.0092 nan 0.0100 0.0000
## 200 0.0084 nan 0.0100 0.0000
##
## - Fold01: shrinkage=0.01, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold01: shrinkage=0.01, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0439 nan 0.0100 0.0003
## 2 0.0434 nan 0.0100 0.0003
## 3 0.0426 nan 0.0100 0.0006
## 4 0.0418 nan 0.0100 0.0007
## 5 0.0411 nan 0.0100 0.0008
## 6 0.0404 nan 0.0100 0.0008
## 7 0.0398 nan 0.0100 0.0003
## 8 0.0392 nan 0.0100 0.0003
## 9 0.0385 nan 0.0100 0.0006
## 10 0.0378 nan 0.0100 0.0004
## 20 0.0330 nan 0.0100 0.0003
## 40 0.0245 nan 0.0100 0.0000
## 60 0.0186 nan 0.0100 0.0000
## 80 0.0143 nan 0.0100 0.0002
## 100 0.0111 nan 0.0100 0.0000
## 120 0.0086 nan 0.0100 0.0001
## 140 0.0070 nan 0.0100 0.0001
## 160 0.0056 nan 0.0100 0.0001
## 180 0.0045 nan 0.0100 0.0000
## 200 0.0036 nan 0.0100 0.0000
##
## - Fold01: shrinkage=0.01, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold01: shrinkage=0.01, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0439 nan 0.0100 0.0004
## 2 0.0434 nan 0.0100 0.0004
## 3 0.0429 nan 0.0100 0.0005
## 4 0.0423 nan 0.0100 0.0007
## 5 0.0415 nan 0.0100 0.0006
## 6 0.0407 nan 0.0100 0.0004
## 7 0.0404 nan 0.0100 0.0001
## 8 0.0398 nan 0.0100 0.0004
## 9 0.0392 nan 0.0100 0.0004
## 10 0.0386 nan 0.0100 0.0006
## 20 0.0337 nan 0.0100 0.0003
## 40 0.0257 nan 0.0100 0.0001
## 60 0.0196 nan 0.0100 0.0001
## 80 0.0155 nan 0.0100 0.0002
## 100 0.0121 nan 0.0100 0.0001
## 120 0.0101 nan 0.0100 0.0000
## 140 0.0082 nan 0.0100 0.0000
## 160 0.0067 nan 0.0100 0.0000
## 180 0.0054 nan 0.0100 -0.0000
## 200 0.0045 nan 0.0100 -0.0000
##
## - Fold01: shrinkage=0.01, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold01: shrinkage=0.01, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0439 nan 0.0100 0.0004
## 2 0.0434 nan 0.0100 0.0006
## 3 0.0429 nan 0.0100 0.0006
## 4 0.0424 nan 0.0100 0.0004
## 5 0.0419 nan 0.0100 0.0001
## 6 0.0415 nan 0.0100 0.0003
## 7 0.0414 nan 0.0100 -0.0003
## 8 0.0407 nan 0.0100 0.0005
## 9 0.0404 nan 0.0100 0.0003
## 10 0.0398 nan 0.0100 0.0006
## 20 0.0351 nan 0.0100 0.0005
## 40 0.0276 nan 0.0100 0.0003
## 60 0.0224 nan 0.0100 0.0002
## 80 0.0189 nan 0.0100 0.0001
## 100 0.0157 nan 0.0100 0.0001
## 120 0.0134 nan 0.0100 0.0001
## 140 0.0118 nan 0.0100 0.0000
## 160 0.0106 nan 0.0100 0.0000
## 180 0.0094 nan 0.0100 -0.0000
## 200 0.0084 nan 0.0100 0.0000
##
## - Fold01: shrinkage=0.01, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold01: shrinkage=0.01, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0438 nan 0.0100 0.0008
## 2 0.0433 nan 0.0100 0.0004
## 3 0.0428 nan 0.0100 0.0005
## 4 0.0420 nan 0.0100 0.0006
## 5 0.0413 nan 0.0100 0.0005
## 6 0.0406 nan 0.0100 0.0005
## 7 0.0399 nan 0.0100 0.0002
## 8 0.0393 nan 0.0100 0.0005
## 9 0.0386 nan 0.0100 0.0008
## 10 0.0382 nan 0.0100 0.0003
## 20 0.0323 nan 0.0100 0.0003
## 40 0.0247 nan 0.0100 0.0002
## 60 0.0184 nan 0.0100 0.0003
## 80 0.0139 nan 0.0100 0.0002
## 100 0.0105 nan 0.0100 0.0002
## 120 0.0083 nan 0.0100 0.0000
## 140 0.0062 nan 0.0100 0.0001
## 160 0.0048 nan 0.0100 0.0000
## 180 0.0039 nan 0.0100 0.0000
## 200 0.0031 nan 0.0100 0.0000
##
## - Fold01: shrinkage=0.01, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold01: shrinkage=0.01, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0438 nan 0.0100 0.0006
## 2 0.0432 nan 0.0100 0.0007
## 3 0.0424 nan 0.0100 0.0007
## 4 0.0418 nan 0.0100 0.0006
## 5 0.0411 nan 0.0100 0.0006
## 6 0.0408 nan 0.0100 -0.0001
## 7 0.0403 nan 0.0100 0.0004
## 8 0.0399 nan 0.0100 0.0004
## 9 0.0392 nan 0.0100 0.0005
## 10 0.0385 nan 0.0100 0.0007
## 20 0.0332 nan 0.0100 0.0003
## 40 0.0254 nan 0.0100 0.0003
## 60 0.0195 nan 0.0100 0.0002
## 80 0.0150 nan 0.0100 0.0001
## 100 0.0115 nan 0.0100 0.0001
## 120 0.0093 nan 0.0100 0.0000
## 140 0.0074 nan 0.0100 0.0000
## 160 0.0059 nan 0.0100 -0.0000
## 180 0.0049 nan 0.0100 0.0000
## 200 0.0040 nan 0.0100 -0.0000
##
## - Fold01: shrinkage=0.01, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold01: shrinkage=0.01, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0438 nan 0.0100 0.0006
## 2 0.0433 nan 0.0100 0.0003
## 3 0.0428 nan 0.0100 0.0004
## 4 0.0423 nan 0.0100 0.0006
## 5 0.0417 nan 0.0100 0.0003
## 6 0.0412 nan 0.0100 0.0004
## 7 0.0407 nan 0.0100 0.0005
## 8 0.0404 nan 0.0100 0.0000
## 9 0.0399 nan 0.0100 0.0005
## 10 0.0394 nan 0.0100 0.0005
## 20 0.0353 nan 0.0100 0.0003
## 40 0.0283 nan 0.0100 0.0002
## 60 0.0232 nan 0.0100 0.0002
## 80 0.0188 nan 0.0100 0.0001
## 100 0.0157 nan 0.0100 0.0000
## 120 0.0132 nan 0.0100 -0.0000
## 140 0.0113 nan 0.0100 0.0001
## 160 0.0096 nan 0.0100 0.0000
## 180 0.0086 nan 0.0100 0.0000
## 200 0.0075 nan 0.0100 0.0000
##
## - Fold01: shrinkage=0.01, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold01: shrinkage=0.05, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0411 nan 0.0500 0.0027
## 2 0.0392 nan 0.0500 0.0014
## 3 0.0372 nan 0.0500 0.0019
## 4 0.0344 nan 0.0500 0.0021
## 5 0.0317 nan 0.0500 0.0022
## 6 0.0297 nan 0.0500 0.0021
## 7 0.0281 nan 0.0500 0.0017
## 8 0.0265 nan 0.0500 0.0016
## 9 0.0252 nan 0.0500 0.0014
## 10 0.0234 nan 0.0500 0.0011
## 20 0.0140 nan 0.0500 0.0006
## 40 0.0060 nan 0.0500 0.0002
## 60 0.0033 nan 0.0500 0.0001
## 80 0.0019 nan 0.0500 0.0000
## 100 0.0012 nan 0.0500 -0.0000
## 120 0.0007 nan 0.0500 0.0000
## 140 0.0004 nan 0.0500 -0.0000
## 160 0.0003 nan 0.0500 -0.0000
## 180 0.0002 nan 0.0500 -0.0000
## 200 0.0001 nan 0.0500 -0.0000
##
## - Fold01: shrinkage=0.05, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold01: shrinkage=0.05, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0415 nan 0.0500 0.0030
## 2 0.0386 nan 0.0500 0.0030
## 3 0.0360 nan 0.0500 0.0026
## 4 0.0335 nan 0.0500 0.0018
## 5 0.0312 nan 0.0500 0.0016
## 6 0.0295 nan 0.0500 0.0013
## 7 0.0274 nan 0.0500 0.0019
## 8 0.0262 nan 0.0500 0.0010
## 9 0.0244 nan 0.0500 0.0009
## 10 0.0232 nan 0.0500 0.0012
## 20 0.0140 nan 0.0500 -0.0001
## 40 0.0062 nan 0.0500 0.0001
## 60 0.0031 nan 0.0500 0.0000
## 80 0.0018 nan 0.0500 0.0000
## 100 0.0011 nan 0.0500 0.0000
## 120 0.0008 nan 0.0500 0.0000
## 140 0.0005 nan 0.0500 -0.0000
## 160 0.0004 nan 0.0500 -0.0000
## 180 0.0003 nan 0.0500 0.0000
## 200 0.0002 nan 0.0500 0.0000
##
## - Fold01: shrinkage=0.05, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold01: shrinkage=0.05, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0409 nan 0.0500 0.0028
## 2 0.0377 nan 0.0500 0.0028
## 3 0.0357 nan 0.0500 0.0014
## 4 0.0340 nan 0.0500 0.0013
## 5 0.0314 nan 0.0500 0.0022
## 6 0.0292 nan 0.0500 0.0009
## 7 0.0286 nan 0.0500 -0.0005
## 8 0.0266 nan 0.0500 0.0012
## 9 0.0256 nan 0.0500 0.0006
## 10 0.0241 nan 0.0500 0.0004
## 20 0.0159 nan 0.0500 0.0008
## 40 0.0083 nan 0.0500 0.0002
## 60 0.0048 nan 0.0500 -0.0001
## 80 0.0029 nan 0.0500 0.0001
## 100 0.0018 nan 0.0500 0.0000
## 120 0.0012 nan 0.0500 0.0000
## 140 0.0008 nan 0.0500 -0.0000
## 160 0.0006 nan 0.0500 0.0000
## 180 0.0005 nan 0.0500 -0.0000
## 200 0.0004 nan 0.0500 -0.0000
##
## - Fold01: shrinkage=0.05, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold01: shrinkage=0.05, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0415 nan 0.0500 0.0006
## 2 0.0395 nan 0.0500 -0.0000
## 3 0.0368 nan 0.0500 0.0019
## 4 0.0342 nan 0.0500 0.0014
## 5 0.0315 nan 0.0500 0.0023
## 6 0.0295 nan 0.0500 0.0011
## 7 0.0277 nan 0.0500 0.0017
## 8 0.0256 nan 0.0500 0.0011
## 9 0.0238 nan 0.0500 0.0014
## 10 0.0225 nan 0.0500 0.0009
## 20 0.0125 nan 0.0500 0.0008
## 40 0.0038 nan 0.0500 -0.0000
## 60 0.0014 nan 0.0500 -0.0000
## 80 0.0006 nan 0.0500 0.0000
## 100 0.0003 nan 0.0500 0.0000
## 120 0.0002 nan 0.0500 -0.0000
## 140 0.0001 nan 0.0500 -0.0000
## 160 0.0001 nan 0.0500 -0.0000
## 180 0.0000 nan 0.0500 -0.0000
## 200 0.0000 nan 0.0500 0.0000
##
## - Fold01: shrinkage=0.05, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold01: shrinkage=0.05, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0421 nan 0.0500 0.0021
## 2 0.0388 nan 0.0500 0.0016
## 3 0.0361 nan 0.0500 0.0015
## 4 0.0335 nan 0.0500 0.0027
## 5 0.0318 nan 0.0500 0.0014
## 6 0.0301 nan 0.0500 0.0010
## 7 0.0281 nan 0.0500 0.0019
## 8 0.0265 nan 0.0500 -0.0001
## 9 0.0252 nan 0.0500 0.0005
## 10 0.0232 nan 0.0500 0.0015
## 20 0.0127 nan 0.0500 0.0006
## 40 0.0046 nan 0.0500 0.0000
## 60 0.0021 nan 0.0500 -0.0001
## 80 0.0010 nan 0.0500 0.0000
## 100 0.0005 nan 0.0500 0.0000
## 120 0.0003 nan 0.0500 0.0000
## 140 0.0002 nan 0.0500 -0.0000
## 160 0.0001 nan 0.0500 -0.0000
## 180 0.0001 nan 0.0500 -0.0000
## 200 0.0000 nan 0.0500 -0.0000
##
## - Fold01: shrinkage=0.05, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold01: shrinkage=0.05, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0418 nan 0.0500 0.0009
## 2 0.0381 nan 0.0500 0.0021
## 3 0.0363 nan 0.0500 0.0006
## 4 0.0346 nan 0.0500 0.0007
## 5 0.0333 nan 0.0500 0.0006
## 6 0.0315 nan 0.0500 0.0012
## 7 0.0296 nan 0.0500 0.0021
## 8 0.0275 nan 0.0500 0.0012
## 9 0.0261 nan 0.0500 0.0015
## 10 0.0251 nan 0.0500 0.0009
## 20 0.0158 nan 0.0500 0.0004
## 40 0.0081 nan 0.0500 0.0001
## 60 0.0047 nan 0.0500 0.0000
## 80 0.0031 nan 0.0500 -0.0000
## 100 0.0021 nan 0.0500 -0.0000
## 120 0.0015 nan 0.0500 -0.0000
## 140 0.0010 nan 0.0500 0.0000
## 160 0.0008 nan 0.0500 -0.0000
## 180 0.0006 nan 0.0500 -0.0000
## 200 0.0005 nan 0.0500 -0.0000
##
## - Fold01: shrinkage=0.05, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold01: shrinkage=0.05, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0417 nan 0.0500 0.0023
## 2 0.0387 nan 0.0500 0.0029
## 3 0.0377 nan 0.0500 -0.0004
## 4 0.0352 nan 0.0500 0.0028
## 5 0.0326 nan 0.0500 0.0022
## 6 0.0298 nan 0.0500 0.0015
## 7 0.0273 nan 0.0500 0.0031
## 8 0.0252 nan 0.0500 0.0009
## 9 0.0235 nan 0.0500 0.0015
## 10 0.0221 nan 0.0500 0.0012
## 20 0.0108 nan 0.0500 0.0003
## 40 0.0030 nan 0.0500 0.0001
## 60 0.0011 nan 0.0500 -0.0000
## 80 0.0005 nan 0.0500 -0.0000
## 100 0.0002 nan 0.0500 -0.0000
## 120 0.0001 nan 0.0500 -0.0000
## 140 0.0000 nan 0.0500 0.0000
## 160 0.0000 nan 0.0500 -0.0000
## 180 0.0000 nan 0.0500 -0.0000
## 200 0.0000 nan 0.0500 -0.0000
##
## - Fold01: shrinkage=0.05, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold01: shrinkage=0.05, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0412 nan 0.0500 0.0027
## 2 0.0382 nan 0.0500 0.0029
## 3 0.0350 nan 0.0500 0.0018
## 4 0.0336 nan 0.0500 0.0011
## 5 0.0321 nan 0.0500 0.0020
## 6 0.0300 nan 0.0500 0.0019
## 7 0.0276 nan 0.0500 0.0016
## 8 0.0252 nan 0.0500 0.0012
## 9 0.0243 nan 0.0500 0.0005
## 10 0.0221 nan 0.0500 0.0011
## 20 0.0122 nan 0.0500 0.0005
## 40 0.0040 nan 0.0500 0.0000
## 60 0.0021 nan 0.0500 0.0000
## 80 0.0011 nan 0.0500 0.0000
## 100 0.0006 nan 0.0500 -0.0000
## 120 0.0004 nan 0.0500 -0.0000
## 140 0.0002 nan 0.0500 -0.0000
## 160 0.0002 nan 0.0500 -0.0000
## 180 0.0001 nan 0.0500 0.0000
## 200 0.0001 nan 0.0500 -0.0000
##
## - Fold01: shrinkage=0.05, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold01: shrinkage=0.05, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0425 nan 0.0500 0.0014
## 2 0.0401 nan 0.0500 0.0022
## 3 0.0378 nan 0.0500 0.0015
## 4 0.0348 nan 0.0500 0.0027
## 5 0.0337 nan 0.0500 0.0002
## 6 0.0326 nan 0.0500 0.0003
## 7 0.0308 nan 0.0500 0.0005
## 8 0.0290 nan 0.0500 0.0015
## 9 0.0280 nan 0.0500 0.0004
## 10 0.0265 nan 0.0500 0.0009
## 20 0.0160 nan 0.0500 0.0005
## 40 0.0084 nan 0.0500 -0.0001
## 60 0.0049 nan 0.0500 -0.0000
## 80 0.0031 nan 0.0500 0.0000
## 100 0.0019 nan 0.0500 -0.0000
## 120 0.0014 nan 0.0500 0.0000
## 140 0.0010 nan 0.0500 -0.0000
## 160 0.0007 nan 0.0500 0.0000
## 180 0.0005 nan 0.0500 -0.0000
## 200 0.0004 nan 0.0500 -0.0000
##
## - Fold01: shrinkage=0.05, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold01: shrinkage=0.10, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0385 nan 0.1000 0.0063
## 2 0.0338 nan 0.1000 0.0050
## 3 0.0287 nan 0.1000 0.0043
## 4 0.0248 nan 0.1000 0.0028
## 5 0.0234 nan 0.1000 0.0011
## 6 0.0201 nan 0.1000 0.0025
## 7 0.0193 nan 0.1000 -0.0002
## 8 0.0179 nan 0.1000 0.0010
## 9 0.0155 nan 0.1000 0.0016
## 10 0.0130 nan 0.1000 0.0032
## 20 0.0058 nan 0.1000 0.0005
## 40 0.0015 nan 0.1000 -0.0000
## 60 0.0006 nan 0.1000 0.0000
## 80 0.0003 nan 0.1000 0.0000
## 100 0.0001 nan 0.1000 0.0000
## 120 0.0001 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold01: shrinkage=0.10, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold01: shrinkage=0.10, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0401 nan 0.1000 0.0025
## 2 0.0349 nan 0.1000 0.0044
## 3 0.0303 nan 0.1000 0.0031
## 4 0.0278 nan 0.1000 0.0022
## 5 0.0254 nan 0.1000 0.0012
## 6 0.0231 nan 0.1000 0.0012
## 7 0.0211 nan 0.1000 0.0013
## 8 0.0189 nan 0.1000 0.0015
## 9 0.0174 nan 0.1000 0.0003
## 10 0.0157 nan 0.1000 0.0021
## 20 0.0068 nan 0.1000 0.0002
## 40 0.0022 nan 0.1000 0.0000
## 60 0.0009 nan 0.1000 0.0000
## 80 0.0004 nan 0.1000 -0.0000
## 100 0.0002 nan 0.1000 0.0000
## 120 0.0001 nan 0.1000 0.0000
## 140 0.0001 nan 0.1000 0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold01: shrinkage=0.10, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold01: shrinkage=0.10, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0407 nan 0.1000 0.0038
## 2 0.0361 nan 0.1000 0.0030
## 3 0.0326 nan 0.1000 0.0018
## 4 0.0290 nan 0.1000 0.0035
## 5 0.0262 nan 0.1000 0.0031
## 6 0.0248 nan 0.1000 0.0004
## 7 0.0223 nan 0.1000 0.0015
## 8 0.0207 nan 0.1000 0.0008
## 9 0.0187 nan 0.1000 0.0008
## 10 0.0171 nan 0.1000 0.0013
## 20 0.0086 nan 0.1000 -0.0002
## 40 0.0033 nan 0.1000 0.0002
## 60 0.0015 nan 0.1000 -0.0001
## 80 0.0007 nan 0.1000 0.0000
## 100 0.0004 nan 0.1000 0.0000
## 120 0.0002 nan 0.1000 -0.0000
## 140 0.0001 nan 0.1000 -0.0000
## 160 0.0001 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold01: shrinkage=0.10, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold01: shrinkage=0.10, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0394 nan 0.1000 0.0028
## 2 0.0323 nan 0.1000 0.0064
## 3 0.0276 nan 0.1000 0.0020
## 4 0.0235 nan 0.1000 0.0036
## 5 0.0204 nan 0.1000 0.0017
## 6 0.0175 nan 0.1000 0.0014
## 7 0.0158 nan 0.1000 0.0007
## 8 0.0149 nan 0.1000 0.0002
## 9 0.0137 nan 0.1000 0.0009
## 10 0.0126 nan 0.1000 -0.0003
## 20 0.0043 nan 0.1000 0.0003
## 40 0.0006 nan 0.1000 0.0000
## 60 0.0001 nan 0.1000 -0.0000
## 80 0.0000 nan 0.1000 0.0000
## 100 0.0000 nan 0.1000 0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold01: shrinkage=0.10, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold01: shrinkage=0.10, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0383 nan 0.1000 0.0062
## 2 0.0339 nan 0.1000 0.0053
## 3 0.0295 nan 0.1000 0.0034
## 4 0.0261 nan 0.1000 0.0034
## 5 0.0229 nan 0.1000 0.0030
## 6 0.0203 nan 0.1000 0.0033
## 7 0.0176 nan 0.1000 0.0005
## 8 0.0159 nan 0.1000 0.0017
## 9 0.0142 nan 0.1000 0.0013
## 10 0.0121 nan 0.1000 0.0019
## 20 0.0045 nan 0.1000 -0.0000
## 40 0.0010 nan 0.1000 0.0000
## 60 0.0004 nan 0.1000 -0.0000
## 80 0.0002 nan 0.1000 -0.0000
## 100 0.0001 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 0.0000
##
## - Fold01: shrinkage=0.10, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold01: shrinkage=0.10, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0376 nan 0.1000 0.0059
## 2 0.0345 nan 0.1000 0.0011
## 3 0.0305 nan 0.1000 0.0031
## 4 0.0286 nan 0.1000 0.0011
## 5 0.0257 nan 0.1000 0.0012
## 6 0.0228 nan 0.1000 0.0028
## 7 0.0216 nan 0.1000 -0.0004
## 8 0.0204 nan 0.1000 0.0011
## 9 0.0179 nan 0.1000 0.0016
## 10 0.0168 nan 0.1000 0.0007
## 20 0.0084 nan 0.1000 0.0001
## 40 0.0034 nan 0.1000 0.0001
## 60 0.0016 nan 0.1000 0.0001
## 80 0.0008 nan 0.1000 -0.0000
## 100 0.0006 nan 0.1000 -0.0000
## 120 0.0004 nan 0.1000 -0.0000
## 140 0.0002 nan 0.1000 -0.0000
## 160 0.0002 nan 0.1000 -0.0000
## 180 0.0001 nan 0.1000 -0.0000
## 200 0.0001 nan 0.1000 -0.0000
##
## - Fold01: shrinkage=0.10, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold01: shrinkage=0.10, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0377 nan 0.1000 0.0054
## 2 0.0312 nan 0.1000 0.0031
## 3 0.0254 nan 0.1000 0.0029
## 4 0.0223 nan 0.1000 0.0020
## 5 0.0198 nan 0.1000 0.0012
## 6 0.0167 nan 0.1000 0.0017
## 7 0.0144 nan 0.1000 0.0014
## 8 0.0122 nan 0.1000 0.0005
## 9 0.0114 nan 0.1000 0.0006
## 10 0.0101 nan 0.1000 0.0007
## 20 0.0033 nan 0.1000 0.0001
## 40 0.0008 nan 0.1000 0.0000
## 60 0.0002 nan 0.1000 -0.0000
## 80 0.0000 nan 0.1000 -0.0000
## 100 0.0000 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 0.0000
## 180 0.0000 nan 0.1000 0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold01: shrinkage=0.10, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold01: shrinkage=0.10, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0402 nan 0.1000 0.0020
## 2 0.0335 nan 0.1000 0.0047
## 3 0.0297 nan 0.1000 0.0034
## 4 0.0258 nan 0.1000 0.0024
## 5 0.0234 nan 0.1000 0.0020
## 6 0.0196 nan 0.1000 0.0024
## 7 0.0172 nan 0.1000 0.0008
## 8 0.0155 nan 0.1000 0.0017
## 9 0.0129 nan 0.1000 0.0010
## 10 0.0110 nan 0.1000 0.0016
## 20 0.0036 nan 0.1000 0.0002
## 40 0.0009 nan 0.1000 -0.0000
## 60 0.0003 nan 0.1000 -0.0000
## 80 0.0001 nan 0.1000 0.0000
## 100 0.0000 nan 0.1000 0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold01: shrinkage=0.10, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold01: shrinkage=0.10, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0402 nan 0.1000 0.0033
## 2 0.0358 nan 0.1000 0.0044
## 3 0.0302 nan 0.1000 0.0047
## 4 0.0260 nan 0.1000 0.0033
## 5 0.0239 nan 0.1000 0.0017
## 6 0.0224 nan 0.1000 0.0009
## 7 0.0202 nan 0.1000 0.0013
## 8 0.0189 nan 0.1000 0.0010
## 9 0.0167 nan 0.1000 0.0011
## 10 0.0160 nan 0.1000 -0.0004
## 20 0.0075 nan 0.1000 -0.0007
## 40 0.0029 nan 0.1000 0.0001
## 60 0.0017 nan 0.1000 -0.0001
## 80 0.0008 nan 0.1000 -0.0001
## 100 0.0005 nan 0.1000 0.0000
## 120 0.0003 nan 0.1000 -0.0000
## 140 0.0002 nan 0.1000 -0.0000
## 160 0.0001 nan 0.1000 0.0000
## 180 0.0001 nan 0.1000 -0.0000
## 200 0.0001 nan 0.1000 -0.0000
##
## - Fold01: shrinkage=0.10, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold02: shrinkage=0.01, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0435 nan 0.0100 0.0001
## 2 0.0431 nan 0.0100 0.0001
## 3 0.0425 nan 0.0100 0.0005
## 4 0.0419 nan 0.0100 0.0004
## 5 0.0417 nan 0.0100 0.0002
## 6 0.0414 nan 0.0100 0.0002
## 7 0.0408 nan 0.0100 0.0006
## 8 0.0403 nan 0.0100 0.0006
## 9 0.0398 nan 0.0100 0.0003
## 10 0.0393 nan 0.0100 0.0005
## 20 0.0345 nan 0.0100 0.0005
## 40 0.0276 nan 0.0100 0.0001
## 60 0.0226 nan 0.0100 0.0001
## 80 0.0185 nan 0.0100 0.0000
## 100 0.0149 nan 0.0100 0.0002
## 120 0.0122 nan 0.0100 -0.0000
## 140 0.0100 nan 0.0100 0.0001
## 160 0.0083 nan 0.0100 0.0001
## 180 0.0070 nan 0.0100 0.0000
## 200 0.0060 nan 0.0100 -0.0000
##
## - Fold02: shrinkage=0.01, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold02: shrinkage=0.01, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0435 nan 0.0100 0.0002
## 2 0.0430 nan 0.0100 0.0002
## 3 0.0425 nan 0.0100 0.0004
## 4 0.0419 nan 0.0100 0.0006
## 5 0.0414 nan 0.0100 0.0003
## 6 0.0408 nan 0.0100 0.0006
## 7 0.0403 nan 0.0100 0.0005
## 8 0.0399 nan 0.0100 0.0002
## 9 0.0396 nan 0.0100 -0.0000
## 10 0.0391 nan 0.0100 0.0005
## 20 0.0342 nan 0.0100 0.0004
## 40 0.0274 nan 0.0100 0.0001
## 60 0.0228 nan 0.0100 -0.0000
## 80 0.0184 nan 0.0100 0.0001
## 100 0.0152 nan 0.0100 0.0001
## 120 0.0125 nan 0.0100 0.0000
## 140 0.0106 nan 0.0100 0.0001
## 160 0.0089 nan 0.0100 0.0000
## 180 0.0076 nan 0.0100 0.0001
## 200 0.0066 nan 0.0100 -0.0000
##
## - Fold02: shrinkage=0.01, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold02: shrinkage=0.01, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0432 nan 0.0100 0.0005
## 2 0.0427 nan 0.0100 0.0006
## 3 0.0421 nan 0.0100 0.0006
## 4 0.0417 nan 0.0100 0.0002
## 5 0.0412 nan 0.0100 0.0004
## 6 0.0408 nan 0.0100 0.0001
## 7 0.0402 nan 0.0100 0.0005
## 8 0.0395 nan 0.0100 0.0005
## 9 0.0392 nan 0.0100 0.0001
## 10 0.0389 nan 0.0100 0.0002
## 20 0.0346 nan 0.0100 0.0003
## 40 0.0279 nan 0.0100 0.0000
## 60 0.0233 nan 0.0100 0.0001
## 80 0.0190 nan 0.0100 0.0002
## 100 0.0158 nan 0.0100 0.0000
## 120 0.0137 nan 0.0100 0.0001
## 140 0.0121 nan 0.0100 -0.0000
## 160 0.0105 nan 0.0100 0.0001
## 180 0.0090 nan 0.0100 -0.0000
## 200 0.0080 nan 0.0100 -0.0000
##
## - Fold02: shrinkage=0.01, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold02: shrinkage=0.01, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0430 nan 0.0100 0.0005
## 2 0.0423 nan 0.0100 0.0006
## 3 0.0418 nan 0.0100 0.0005
## 4 0.0412 nan 0.0100 0.0004
## 5 0.0405 nan 0.0100 0.0005
## 6 0.0400 nan 0.0100 0.0002
## 7 0.0394 nan 0.0100 0.0003
## 8 0.0388 nan 0.0100 0.0004
## 9 0.0384 nan 0.0100 0.0003
## 10 0.0379 nan 0.0100 0.0005
## 20 0.0333 nan 0.0100 0.0005
## 40 0.0257 nan 0.0100 0.0001
## 60 0.0193 nan 0.0100 0.0002
## 80 0.0153 nan 0.0100 0.0001
## 100 0.0120 nan 0.0100 0.0001
## 120 0.0094 nan 0.0100 0.0000
## 140 0.0077 nan 0.0100 0.0001
## 160 0.0060 nan 0.0100 0.0001
## 180 0.0048 nan 0.0100 -0.0000
## 200 0.0039 nan 0.0100 0.0000
##
## - Fold02: shrinkage=0.01, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold02: shrinkage=0.01, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0433 nan 0.0100 0.0002
## 2 0.0426 nan 0.0100 0.0004
## 3 0.0422 nan 0.0100 0.0002
## 4 0.0417 nan 0.0100 0.0003
## 5 0.0412 nan 0.0100 0.0002
## 6 0.0406 nan 0.0100 0.0002
## 7 0.0401 nan 0.0100 0.0001
## 8 0.0395 nan 0.0100 0.0007
## 9 0.0390 nan 0.0100 0.0004
## 10 0.0387 nan 0.0100 0.0001
## 20 0.0337 nan 0.0100 0.0005
## 40 0.0264 nan 0.0100 0.0002
## 60 0.0210 nan 0.0100 0.0003
## 80 0.0166 nan 0.0100 0.0002
## 100 0.0134 nan 0.0100 0.0001
## 120 0.0104 nan 0.0100 0.0001
## 140 0.0084 nan 0.0100 0.0001
## 160 0.0068 nan 0.0100 0.0001
## 180 0.0056 nan 0.0100 0.0000
## 200 0.0046 nan 0.0100 0.0000
##
## - Fold02: shrinkage=0.01, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold02: shrinkage=0.01, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0433 nan 0.0100 0.0001
## 2 0.0426 nan 0.0100 0.0003
## 3 0.0420 nan 0.0100 0.0006
## 4 0.0417 nan 0.0100 0.0003
## 5 0.0414 nan 0.0100 0.0002
## 6 0.0407 nan 0.0100 0.0006
## 7 0.0401 nan 0.0100 0.0006
## 8 0.0399 nan 0.0100 -0.0000
## 9 0.0393 nan 0.0100 0.0005
## 10 0.0386 nan 0.0100 0.0006
## 20 0.0341 nan 0.0100 0.0003
## 40 0.0268 nan 0.0100 0.0002
## 60 0.0218 nan 0.0100 0.0001
## 80 0.0181 nan 0.0100 0.0000
## 100 0.0149 nan 0.0100 0.0001
## 120 0.0129 nan 0.0100 0.0001
## 140 0.0111 nan 0.0100 0.0000
## 160 0.0097 nan 0.0100 0.0001
## 180 0.0087 nan 0.0100 0.0000
## 200 0.0078 nan 0.0100 0.0000
##
## - Fold02: shrinkage=0.01, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold02: shrinkage=0.01, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0430 nan 0.0100 0.0008
## 2 0.0423 nan 0.0100 0.0005
## 3 0.0415 nan 0.0100 0.0005
## 4 0.0407 nan 0.0100 0.0007
## 5 0.0400 nan 0.0100 0.0005
## 6 0.0396 nan 0.0100 0.0005
## 7 0.0390 nan 0.0100 0.0003
## 8 0.0383 nan 0.0100 0.0006
## 9 0.0381 nan 0.0100 -0.0001
## 10 0.0379 nan 0.0100 0.0001
## 20 0.0326 nan 0.0100 0.0001
## 40 0.0243 nan 0.0100 0.0002
## 60 0.0181 nan 0.0100 0.0003
## 80 0.0143 nan 0.0100 0.0001
## 100 0.0111 nan 0.0100 0.0002
## 120 0.0086 nan 0.0100 -0.0000
## 140 0.0068 nan 0.0100 0.0000
## 160 0.0054 nan 0.0100 -0.0000
## 180 0.0044 nan 0.0100 -0.0000
## 200 0.0036 nan 0.0100 0.0000
##
## - Fold02: shrinkage=0.01, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold02: shrinkage=0.01, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0433 nan 0.0100 0.0003
## 2 0.0425 nan 0.0100 0.0008
## 3 0.0419 nan 0.0100 0.0006
## 4 0.0412 nan 0.0100 0.0005
## 5 0.0405 nan 0.0100 0.0004
## 6 0.0400 nan 0.0100 0.0005
## 7 0.0397 nan 0.0100 -0.0003
## 8 0.0390 nan 0.0100 0.0001
## 9 0.0384 nan 0.0100 0.0005
## 10 0.0378 nan 0.0100 0.0006
## 20 0.0329 nan 0.0100 0.0005
## 40 0.0256 nan 0.0100 0.0003
## 60 0.0200 nan 0.0100 0.0002
## 80 0.0157 nan 0.0100 0.0000
## 100 0.0124 nan 0.0100 0.0000
## 120 0.0096 nan 0.0100 0.0001
## 140 0.0078 nan 0.0100 0.0001
## 160 0.0061 nan 0.0100 0.0000
## 180 0.0050 nan 0.0100 0.0000
## 200 0.0041 nan 0.0100 0.0000
##
## - Fold02: shrinkage=0.01, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold02: shrinkage=0.01, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0433 nan 0.0100 0.0004
## 2 0.0427 nan 0.0100 0.0006
## 3 0.0423 nan 0.0100 0.0002
## 4 0.0418 nan 0.0100 0.0005
## 5 0.0414 nan 0.0100 0.0003
## 6 0.0408 nan 0.0100 0.0005
## 7 0.0404 nan 0.0100 0.0002
## 8 0.0402 nan 0.0100 -0.0002
## 9 0.0398 nan 0.0100 0.0003
## 10 0.0394 nan 0.0100 0.0002
## 20 0.0354 nan 0.0100 0.0003
## 40 0.0280 nan 0.0100 0.0002
## 60 0.0224 nan 0.0100 0.0002
## 80 0.0182 nan 0.0100 -0.0001
## 100 0.0153 nan 0.0100 0.0001
## 120 0.0131 nan 0.0100 0.0001
## 140 0.0113 nan 0.0100 0.0001
## 160 0.0100 nan 0.0100 0.0000
## 180 0.0089 nan 0.0100 0.0000
## 200 0.0080 nan 0.0100 0.0000
##
## - Fold02: shrinkage=0.01, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold02: shrinkage=0.05, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0409 nan 0.0500 0.0015
## 2 0.0379 nan 0.0500 0.0029
## 3 0.0359 nan 0.0500 0.0017
## 4 0.0328 nan 0.0500 0.0021
## 5 0.0308 nan 0.0500 0.0015
## 6 0.0281 nan 0.0500 0.0018
## 7 0.0263 nan 0.0500 0.0016
## 8 0.0250 nan 0.0500 0.0007
## 9 0.0235 nan 0.0500 0.0009
## 10 0.0221 nan 0.0500 0.0012
## 20 0.0136 nan 0.0500 0.0002
## 40 0.0062 nan 0.0500 0.0003
## 60 0.0031 nan 0.0500 0.0001
## 80 0.0018 nan 0.0500 0.0000
## 100 0.0011 nan 0.0500 -0.0001
## 120 0.0007 nan 0.0500 -0.0000
## 140 0.0004 nan 0.0500 0.0000
## 160 0.0003 nan 0.0500 -0.0000
## 180 0.0002 nan 0.0500 0.0000
## 200 0.0001 nan 0.0500 -0.0000
##
## - Fold02: shrinkage=0.05, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold02: shrinkage=0.05, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0416 nan 0.0500 0.0010
## 2 0.0392 nan 0.0500 0.0017
## 3 0.0372 nan 0.0500 0.0022
## 4 0.0352 nan 0.0500 0.0013
## 5 0.0328 nan 0.0500 0.0018
## 6 0.0310 nan 0.0500 0.0016
## 7 0.0298 nan 0.0500 0.0002
## 8 0.0281 nan 0.0500 0.0009
## 9 0.0263 nan 0.0500 0.0017
## 10 0.0244 nan 0.0500 0.0016
## 20 0.0145 nan 0.0500 -0.0001
## 40 0.0061 nan 0.0500 0.0002
## 60 0.0037 nan 0.0500 -0.0000
## 80 0.0020 nan 0.0500 0.0000
## 100 0.0013 nan 0.0500 -0.0001
## 120 0.0008 nan 0.0500 0.0000
## 140 0.0005 nan 0.0500 0.0000
## 160 0.0003 nan 0.0500 -0.0000
## 180 0.0003 nan 0.0500 -0.0000
## 200 0.0002 nan 0.0500 -0.0000
##
## - Fold02: shrinkage=0.05, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold02: shrinkage=0.05, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0405 nan 0.0500 0.0031
## 2 0.0389 nan 0.0500 0.0014
## 3 0.0379 nan 0.0500 0.0001
## 4 0.0363 nan 0.0500 0.0019
## 5 0.0341 nan 0.0500 0.0019
## 6 0.0320 nan 0.0500 0.0021
## 7 0.0304 nan 0.0500 0.0010
## 8 0.0285 nan 0.0500 0.0017
## 9 0.0268 nan 0.0500 0.0015
## 10 0.0252 nan 0.0500 0.0014
## 20 0.0167 nan 0.0500 0.0006
## 40 0.0089 nan 0.0500 -0.0001
## 60 0.0054 nan 0.0500 -0.0001
## 80 0.0032 nan 0.0500 0.0000
## 100 0.0023 nan 0.0500 -0.0000
## 120 0.0014 nan 0.0500 0.0000
## 140 0.0010 nan 0.0500 0.0000
## 160 0.0007 nan 0.0500 -0.0000
## 180 0.0005 nan 0.0500 0.0000
## 200 0.0004 nan 0.0500 -0.0000
##
## - Fold02: shrinkage=0.05, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold02: shrinkage=0.05, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0409 nan 0.0500 0.0017
## 2 0.0402 nan 0.0500 -0.0006
## 3 0.0380 nan 0.0500 0.0010
## 4 0.0351 nan 0.0500 0.0025
## 5 0.0327 nan 0.0500 0.0021
## 6 0.0313 nan 0.0500 0.0010
## 7 0.0292 nan 0.0500 0.0016
## 8 0.0274 nan 0.0500 0.0014
## 9 0.0253 nan 0.0500 0.0014
## 10 0.0235 nan 0.0500 0.0019
## 20 0.0126 nan 0.0500 0.0006
## 40 0.0037 nan 0.0500 0.0003
## 60 0.0013 nan 0.0500 0.0000
## 80 0.0006 nan 0.0500 -0.0000
## 100 0.0003 nan 0.0500 -0.0000
## 120 0.0001 nan 0.0500 -0.0000
## 140 0.0001 nan 0.0500 -0.0000
## 160 0.0000 nan 0.0500 0.0000
## 180 0.0000 nan 0.0500 -0.0000
## 200 0.0000 nan 0.0500 -0.0000
##
## - Fold02: shrinkage=0.05, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold02: shrinkage=0.05, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0409 nan 0.0500 0.0026
## 2 0.0379 nan 0.0500 0.0021
## 3 0.0351 nan 0.0500 0.0027
## 4 0.0318 nan 0.0500 0.0023
## 5 0.0300 nan 0.0500 0.0016
## 6 0.0280 nan 0.0500 0.0018
## 7 0.0260 nan 0.0500 0.0009
## 8 0.0247 nan 0.0500 0.0005
## 9 0.0232 nan 0.0500 0.0001
## 10 0.0211 nan 0.0500 0.0013
## 20 0.0122 nan 0.0500 0.0002
## 40 0.0045 nan 0.0500 0.0001
## 60 0.0023 nan 0.0500 -0.0000
## 80 0.0012 nan 0.0500 -0.0000
## 100 0.0008 nan 0.0500 -0.0000
## 120 0.0005 nan 0.0500 -0.0000
## 140 0.0003 nan 0.0500 -0.0000
## 160 0.0002 nan 0.0500 -0.0000
## 180 0.0001 nan 0.0500 0.0000
## 200 0.0001 nan 0.0500 0.0000
##
## - Fold02: shrinkage=0.05, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold02: shrinkage=0.05, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0406 nan 0.0500 0.0019
## 2 0.0384 nan 0.0500 0.0023
## 3 0.0354 nan 0.0500 0.0021
## 4 0.0332 nan 0.0500 0.0021
## 5 0.0318 nan 0.0500 0.0017
## 6 0.0295 nan 0.0500 0.0018
## 7 0.0281 nan 0.0500 0.0015
## 8 0.0263 nan 0.0500 0.0012
## 9 0.0253 nan 0.0500 0.0000
## 10 0.0237 nan 0.0500 0.0008
## 20 0.0143 nan 0.0500 0.0007
## 40 0.0085 nan 0.0500 0.0000
## 60 0.0051 nan 0.0500 0.0001
## 80 0.0033 nan 0.0500 -0.0000
## 100 0.0023 nan 0.0500 -0.0001
## 120 0.0017 nan 0.0500 -0.0001
## 140 0.0013 nan 0.0500 -0.0000
## 160 0.0010 nan 0.0500 -0.0000
## 180 0.0007 nan 0.0500 0.0000
## 200 0.0006 nan 0.0500 -0.0000
##
## - Fold02: shrinkage=0.05, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold02: shrinkage=0.05, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0406 nan 0.0500 0.0031
## 2 0.0366 nan 0.0500 0.0028
## 3 0.0335 nan 0.0500 0.0026
## 4 0.0323 nan 0.0500 -0.0002
## 5 0.0296 nan 0.0500 0.0026
## 6 0.0279 nan 0.0500 0.0002
## 7 0.0259 nan 0.0500 0.0018
## 8 0.0247 nan 0.0500 0.0015
## 9 0.0231 nan 0.0500 0.0007
## 10 0.0220 nan 0.0500 -0.0001
## 20 0.0119 nan 0.0500 0.0004
## 40 0.0036 nan 0.0500 0.0001
## 60 0.0012 nan 0.0500 0.0000
## 80 0.0005 nan 0.0500 -0.0000
## 100 0.0002 nan 0.0500 -0.0000
## 120 0.0001 nan 0.0500 0.0000
## 140 0.0000 nan 0.0500 -0.0000
## 160 0.0000 nan 0.0500 -0.0000
## 180 0.0000 nan 0.0500 -0.0000
## 200 0.0000 nan 0.0500 0.0000
##
## - Fold02: shrinkage=0.05, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold02: shrinkage=0.05, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0414 nan 0.0500 0.0006
## 2 0.0388 nan 0.0500 0.0021
## 3 0.0360 nan 0.0500 0.0027
## 4 0.0342 nan 0.0500 0.0012
## 5 0.0324 nan 0.0500 0.0016
## 6 0.0298 nan 0.0500 0.0011
## 7 0.0278 nan 0.0500 0.0017
## 8 0.0266 nan 0.0500 0.0008
## 9 0.0255 nan 0.0500 -0.0002
## 10 0.0246 nan 0.0500 0.0004
## 20 0.0125 nan 0.0500 0.0002
## 40 0.0047 nan 0.0500 -0.0000
## 60 0.0023 nan 0.0500 0.0001
## 80 0.0011 nan 0.0500 0.0000
## 100 0.0005 nan 0.0500 -0.0000
## 120 0.0003 nan 0.0500 -0.0000
## 140 0.0002 nan 0.0500 -0.0000
## 160 0.0001 nan 0.0500 -0.0000
## 180 0.0001 nan 0.0500 -0.0000
## 200 0.0001 nan 0.0500 -0.0000
##
## - Fold02: shrinkage=0.05, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold02: shrinkage=0.05, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0414 nan 0.0500 0.0025
## 2 0.0380 nan 0.0500 0.0025
## 3 0.0365 nan 0.0500 0.0013
## 4 0.0345 nan 0.0500 0.0023
## 5 0.0324 nan 0.0500 0.0018
## 6 0.0305 nan 0.0500 0.0012
## 7 0.0283 nan 0.0500 0.0017
## 8 0.0264 nan 0.0500 0.0012
## 9 0.0253 nan 0.0500 0.0014
## 10 0.0245 nan 0.0500 0.0004
## 20 0.0158 nan 0.0500 0.0001
## 40 0.0074 nan 0.0500 0.0002
## 60 0.0046 nan 0.0500 0.0000
## 80 0.0031 nan 0.0500 0.0001
## 100 0.0020 nan 0.0500 -0.0000
## 120 0.0014 nan 0.0500 0.0000
## 140 0.0009 nan 0.0500 -0.0000
## 160 0.0007 nan 0.0500 0.0000
## 180 0.0006 nan 0.0500 -0.0000
## 200 0.0004 nan 0.0500 0.0000
##
## - Fold02: shrinkage=0.05, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold02: shrinkage=0.10, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0379 nan 0.1000 0.0052
## 2 0.0323 nan 0.1000 0.0045
## 3 0.0303 nan 0.1000 0.0014
## 4 0.0265 nan 0.1000 0.0013
## 5 0.0245 nan 0.1000 0.0016
## 6 0.0222 nan 0.1000 0.0018
## 7 0.0202 nan 0.1000 0.0016
## 8 0.0181 nan 0.1000 0.0019
## 9 0.0176 nan 0.1000 0.0001
## 10 0.0155 nan 0.1000 0.0009
## 20 0.0067 nan 0.1000 0.0000
## 40 0.0016 nan 0.1000 -0.0000
## 60 0.0007 nan 0.1000 -0.0000
## 80 0.0003 nan 0.1000 -0.0000
## 100 0.0001 nan 0.1000 -0.0000
## 120 0.0001 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold02: shrinkage=0.10, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold02: shrinkage=0.10, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0387 nan 0.1000 0.0059
## 2 0.0342 nan 0.1000 0.0011
## 3 0.0316 nan 0.1000 0.0003
## 4 0.0281 nan 0.1000 0.0023
## 5 0.0253 nan 0.1000 0.0032
## 6 0.0231 nan 0.1000 0.0017
## 7 0.0206 nan 0.1000 0.0016
## 8 0.0201 nan 0.1000 -0.0006
## 9 0.0186 nan 0.1000 0.0007
## 10 0.0179 nan 0.1000 0.0003
## 20 0.0079 nan 0.1000 0.0005
## 40 0.0025 nan 0.1000 -0.0001
## 60 0.0014 nan 0.1000 -0.0000
## 80 0.0007 nan 0.1000 0.0000
## 100 0.0004 nan 0.1000 0.0000
## 120 0.0002 nan 0.1000 -0.0000
## 140 0.0001 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold02: shrinkage=0.10, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold02: shrinkage=0.10, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0379 nan 0.1000 0.0036
## 2 0.0353 nan 0.1000 0.0008
## 3 0.0321 nan 0.1000 0.0025
## 4 0.0283 nan 0.1000 0.0024
## 5 0.0249 nan 0.1000 0.0032
## 6 0.0226 nan 0.1000 0.0025
## 7 0.0205 nan 0.1000 0.0022
## 8 0.0185 nan 0.1000 0.0015
## 9 0.0174 nan 0.1000 0.0009
## 10 0.0175 nan 0.1000 -0.0018
## 20 0.0087 nan 0.1000 0.0004
## 40 0.0031 nan 0.1000 -0.0002
## 60 0.0015 nan 0.1000 0.0000
## 80 0.0007 nan 0.1000 0.0000
## 100 0.0004 nan 0.1000 0.0000
## 120 0.0003 nan 0.1000 -0.0000
## 140 0.0002 nan 0.1000 0.0000
## 160 0.0001 nan 0.1000 -0.0000
## 180 0.0001 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 0.0000
##
## - Fold02: shrinkage=0.10, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold02: shrinkage=0.10, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0405 nan 0.1000 -0.0002
## 2 0.0344 nan 0.1000 0.0019
## 3 0.0293 nan 0.1000 0.0032
## 4 0.0248 nan 0.1000 0.0033
## 5 0.0228 nan 0.1000 0.0001
## 6 0.0210 nan 0.1000 0.0017
## 7 0.0188 nan 0.1000 0.0027
## 8 0.0171 nan 0.1000 0.0013
## 9 0.0165 nan 0.1000 -0.0017
## 10 0.0142 nan 0.1000 0.0005
## 20 0.0042 nan 0.1000 0.0001
## 40 0.0005 nan 0.1000 0.0000
## 60 0.0001 nan 0.1000 -0.0000
## 80 0.0000 nan 0.1000 -0.0000
## 100 0.0000 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold02: shrinkage=0.10, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold02: shrinkage=0.10, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0372 nan 0.1000 0.0073
## 2 0.0313 nan 0.1000 0.0055
## 3 0.0270 nan 0.1000 0.0038
## 4 0.0224 nan 0.1000 0.0024
## 5 0.0209 nan 0.1000 -0.0000
## 6 0.0176 nan 0.1000 0.0030
## 7 0.0149 nan 0.1000 0.0015
## 8 0.0131 nan 0.1000 0.0007
## 9 0.0122 nan 0.1000 0.0005
## 10 0.0110 nan 0.1000 0.0007
## 20 0.0034 nan 0.1000 0.0004
## 40 0.0008 nan 0.1000 -0.0001
## 60 0.0003 nan 0.1000 0.0000
## 80 0.0001 nan 0.1000 -0.0000
## 100 0.0001 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 0.0000
##
## - Fold02: shrinkage=0.10, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold02: shrinkage=0.10, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0381 nan 0.1000 0.0058
## 2 0.0322 nan 0.1000 0.0049
## 3 0.0315 nan 0.1000 -0.0020
## 4 0.0280 nan 0.1000 0.0035
## 5 0.0256 nan 0.1000 0.0006
## 6 0.0240 nan 0.1000 0.0006
## 7 0.0217 nan 0.1000 0.0023
## 8 0.0204 nan 0.1000 0.0009
## 9 0.0200 nan 0.1000 -0.0000
## 10 0.0184 nan 0.1000 0.0018
## 20 0.0101 nan 0.1000 0.0003
## 40 0.0040 nan 0.1000 0.0001
## 60 0.0021 nan 0.1000 -0.0002
## 80 0.0013 nan 0.1000 -0.0001
## 100 0.0006 nan 0.1000 -0.0000
## 120 0.0004 nan 0.1000 -0.0000
## 140 0.0002 nan 0.1000 -0.0000
## 160 0.0001 nan 0.1000 -0.0000
## 180 0.0001 nan 0.1000 0.0000
## 200 0.0001 nan 0.1000 -0.0000
##
## - Fold02: shrinkage=0.10, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold02: shrinkage=0.10, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0377 nan 0.1000 0.0041
## 2 0.0327 nan 0.1000 0.0045
## 3 0.0257 nan 0.1000 0.0061
## 4 0.0214 nan 0.1000 0.0028
## 5 0.0180 nan 0.1000 0.0025
## 6 0.0151 nan 0.1000 0.0016
## 7 0.0130 nan 0.1000 0.0014
## 8 0.0113 nan 0.1000 0.0012
## 9 0.0104 nan 0.1000 0.0005
## 10 0.0094 nan 0.1000 0.0003
## 20 0.0032 nan 0.1000 0.0002
## 40 0.0005 nan 0.1000 -0.0000
## 60 0.0001 nan 0.1000 0.0000
## 80 0.0000 nan 0.1000 -0.0000
## 100 0.0000 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold02: shrinkage=0.10, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold02: shrinkage=0.10, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0380 nan 0.1000 0.0029
## 2 0.0330 nan 0.1000 0.0040
## 3 0.0288 nan 0.1000 0.0027
## 4 0.0257 nan 0.1000 0.0039
## 5 0.0216 nan 0.1000 0.0032
## 6 0.0189 nan 0.1000 0.0023
## 7 0.0159 nan 0.1000 0.0016
## 8 0.0145 nan 0.1000 0.0009
## 9 0.0136 nan 0.1000 0.0009
## 10 0.0126 nan 0.1000 0.0007
## 20 0.0056 nan 0.1000 0.0002
## 40 0.0010 nan 0.1000 -0.0000
## 60 0.0002 nan 0.1000 -0.0000
## 80 0.0001 nan 0.1000 -0.0000
## 100 0.0000 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold02: shrinkage=0.10, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold02: shrinkage=0.10, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0379 nan 0.1000 0.0057
## 2 0.0360 nan 0.1000 0.0018
## 3 0.0337 nan 0.1000 -0.0003
## 4 0.0312 nan 0.1000 0.0010
## 5 0.0275 nan 0.1000 0.0022
## 6 0.0243 nan 0.1000 0.0029
## 7 0.0233 nan 0.1000 -0.0004
## 8 0.0212 nan 0.1000 0.0017
## 9 0.0188 nan 0.1000 0.0023
## 10 0.0179 nan 0.1000 -0.0001
## 20 0.0096 nan 0.1000 0.0007
## 40 0.0038 nan 0.1000 0.0001
## 60 0.0018 nan 0.1000 -0.0001
## 80 0.0012 nan 0.1000 0.0000
## 100 0.0007 nan 0.1000 -0.0000
## 120 0.0004 nan 0.1000 -0.0000
## 140 0.0003 nan 0.1000 -0.0000
## 160 0.0002 nan 0.1000 -0.0000
## 180 0.0001 nan 0.1000 -0.0000
## 200 0.0001 nan 0.1000 -0.0000
##
## - Fold02: shrinkage=0.10, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold03: shrinkage=0.01, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0368 nan 0.0100 0.0005
## 2 0.0363 nan 0.0100 0.0002
## 3 0.0358 nan 0.0100 0.0005
## 4 0.0353 nan 0.0100 0.0005
## 5 0.0349 nan 0.0100 0.0002
## 6 0.0344 nan 0.0100 0.0005
## 7 0.0341 nan 0.0100 0.0001
## 8 0.0336 nan 0.0100 0.0002
## 9 0.0334 nan 0.0100 0.0002
## 10 0.0329 nan 0.0100 0.0005
## 20 0.0288 nan 0.0100 0.0002
## 40 0.0233 nan 0.0100 0.0002
## 60 0.0190 nan 0.0100 0.0001
## 80 0.0159 nan 0.0100 0.0002
## 100 0.0129 nan 0.0100 0.0000
## 120 0.0110 nan 0.0100 -0.0000
## 140 0.0093 nan 0.0100 0.0000
## 160 0.0079 nan 0.0100 0.0001
## 180 0.0068 nan 0.0100 0.0001
## 200 0.0056 nan 0.0100 0.0001
##
## - Fold03: shrinkage=0.01, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold03: shrinkage=0.01, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0369 nan 0.0100 0.0005
## 2 0.0365 nan 0.0100 0.0001
## 3 0.0362 nan 0.0100 0.0004
## 4 0.0357 nan 0.0100 0.0005
## 5 0.0351 nan 0.0100 0.0006
## 6 0.0346 nan 0.0100 0.0005
## 7 0.0341 nan 0.0100 0.0003
## 8 0.0337 nan 0.0100 0.0005
## 9 0.0332 nan 0.0100 0.0003
## 10 0.0329 nan 0.0100 -0.0001
## 20 0.0293 nan 0.0100 0.0004
## 40 0.0237 nan 0.0100 0.0003
## 60 0.0190 nan 0.0100 0.0001
## 80 0.0157 nan 0.0100 0.0000
## 100 0.0131 nan 0.0100 0.0001
## 120 0.0109 nan 0.0100 0.0000
## 140 0.0092 nan 0.0100 -0.0000
## 160 0.0079 nan 0.0100 0.0001
## 180 0.0069 nan 0.0100 0.0000
## 200 0.0059 nan 0.0100 0.0001
##
## - Fold03: shrinkage=0.01, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold03: shrinkage=0.01, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0369 nan 0.0100 0.0004
## 2 0.0364 nan 0.0100 0.0005
## 3 0.0361 nan 0.0100 0.0004
## 4 0.0355 nan 0.0100 0.0005
## 5 0.0352 nan 0.0100 0.0003
## 6 0.0347 nan 0.0100 0.0001
## 7 0.0343 nan 0.0100 0.0005
## 8 0.0338 nan 0.0100 0.0005
## 9 0.0334 nan 0.0100 0.0004
## 10 0.0331 nan 0.0100 0.0001
## 20 0.0296 nan 0.0100 0.0004
## 40 0.0239 nan 0.0100 0.0002
## 60 0.0200 nan 0.0100 0.0002
## 80 0.0166 nan 0.0100 -0.0001
## 100 0.0141 nan 0.0100 0.0001
## 120 0.0122 nan 0.0100 0.0001
## 140 0.0108 nan 0.0100 -0.0000
## 160 0.0096 nan 0.0100 -0.0000
## 180 0.0084 nan 0.0100 -0.0000
## 200 0.0076 nan 0.0100 -0.0000
##
## - Fold03: shrinkage=0.01, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold03: shrinkage=0.01, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0369 nan 0.0100 0.0004
## 2 0.0364 nan 0.0100 0.0005
## 3 0.0358 nan 0.0100 0.0004
## 4 0.0352 nan 0.0100 0.0003
## 5 0.0346 nan 0.0100 0.0005
## 6 0.0342 nan 0.0100 0.0003
## 7 0.0336 nan 0.0100 0.0004
## 8 0.0330 nan 0.0100 0.0005
## 9 0.0325 nan 0.0100 0.0006
## 10 0.0319 nan 0.0100 0.0003
## 20 0.0276 nan 0.0100 0.0004
## 40 0.0212 nan 0.0100 0.0002
## 60 0.0164 nan 0.0100 0.0000
## 80 0.0127 nan 0.0100 -0.0000
## 100 0.0099 nan 0.0100 0.0001
## 120 0.0078 nan 0.0100 0.0000
## 140 0.0063 nan 0.0100 0.0000
## 160 0.0050 nan 0.0100 -0.0000
## 180 0.0042 nan 0.0100 0.0000
## 200 0.0035 nan 0.0100 0.0000
##
## - Fold03: shrinkage=0.01, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold03: shrinkage=0.01, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0368 nan 0.0100 0.0005
## 2 0.0364 nan 0.0100 0.0005
## 3 0.0358 nan 0.0100 0.0003
## 4 0.0355 nan 0.0100 0.0002
## 5 0.0351 nan 0.0100 0.0002
## 6 0.0345 nan 0.0100 0.0004
## 7 0.0339 nan 0.0100 0.0006
## 8 0.0335 nan 0.0100 0.0002
## 9 0.0331 nan 0.0100 -0.0001
## 10 0.0328 nan 0.0100 0.0003
## 20 0.0282 nan 0.0100 0.0003
## 40 0.0219 nan 0.0100 0.0000
## 60 0.0168 nan 0.0100 0.0002
## 80 0.0134 nan 0.0100 0.0000
## 100 0.0107 nan 0.0100 0.0001
## 120 0.0088 nan 0.0100 0.0001
## 140 0.0071 nan 0.0100 0.0000
## 160 0.0060 nan 0.0100 0.0001
## 180 0.0051 nan 0.0100 0.0000
## 200 0.0042 nan 0.0100 0.0000
##
## - Fold03: shrinkage=0.01, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold03: shrinkage=0.01, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0370 nan 0.0100 0.0003
## 2 0.0367 nan 0.0100 0.0002
## 3 0.0362 nan 0.0100 0.0005
## 4 0.0357 nan 0.0100 0.0005
## 5 0.0352 nan 0.0100 0.0005
## 6 0.0348 nan 0.0100 0.0001
## 7 0.0345 nan 0.0100 0.0003
## 8 0.0342 nan 0.0100 0.0003
## 9 0.0338 nan 0.0100 0.0004
## 10 0.0334 nan 0.0100 0.0004
## 20 0.0294 nan 0.0100 0.0002
## 40 0.0232 nan 0.0100 0.0001
## 60 0.0189 nan 0.0100 0.0001
## 80 0.0155 nan 0.0100 0.0002
## 100 0.0131 nan 0.0100 0.0001
## 120 0.0113 nan 0.0100 0.0001
## 140 0.0102 nan 0.0100 0.0000
## 160 0.0090 nan 0.0100 0.0001
## 180 0.0080 nan 0.0100 0.0000
## 200 0.0073 nan 0.0100 -0.0000
##
## - Fold03: shrinkage=0.01, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold03: shrinkage=0.01, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0368 nan 0.0100 0.0005
## 2 0.0363 nan 0.0100 0.0004
## 3 0.0356 nan 0.0100 0.0004
## 4 0.0351 nan 0.0100 0.0002
## 5 0.0346 nan 0.0100 0.0004
## 6 0.0341 nan 0.0100 0.0004
## 7 0.0336 nan 0.0100 0.0005
## 8 0.0329 nan 0.0100 0.0005
## 9 0.0323 nan 0.0100 0.0003
## 10 0.0318 nan 0.0100 0.0005
## 20 0.0270 nan 0.0100 0.0003
## 40 0.0202 nan 0.0100 0.0002
## 60 0.0154 nan 0.0100 0.0001
## 80 0.0119 nan 0.0100 0.0001
## 100 0.0092 nan 0.0100 0.0000
## 120 0.0071 nan 0.0100 0.0001
## 140 0.0057 nan 0.0100 0.0000
## 160 0.0044 nan 0.0100 0.0000
## 180 0.0035 nan 0.0100 -0.0000
## 200 0.0028 nan 0.0100 0.0000
##
## - Fold03: shrinkage=0.01, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold03: shrinkage=0.01, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0371 nan 0.0100 0.0001
## 2 0.0366 nan 0.0100 0.0002
## 3 0.0361 nan 0.0100 0.0002
## 4 0.0355 nan 0.0100 0.0005
## 5 0.0349 nan 0.0100 0.0003
## 6 0.0343 nan 0.0100 0.0003
## 7 0.0339 nan 0.0100 0.0004
## 8 0.0333 nan 0.0100 0.0003
## 9 0.0330 nan 0.0100 0.0002
## 10 0.0325 nan 0.0100 0.0004
## 20 0.0286 nan 0.0100 0.0003
## 40 0.0217 nan 0.0100 0.0002
## 60 0.0172 nan 0.0100 0.0002
## 80 0.0135 nan 0.0100 0.0000
## 100 0.0108 nan 0.0100 0.0001
## 120 0.0088 nan 0.0100 0.0001
## 140 0.0069 nan 0.0100 0.0001
## 160 0.0057 nan 0.0100 0.0000
## 180 0.0047 nan 0.0100 0.0000
## 200 0.0039 nan 0.0100 0.0000
##
## - Fold03: shrinkage=0.01, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold03: shrinkage=0.01, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0370 nan 0.0100 0.0001
## 2 0.0368 nan 0.0100 -0.0000
## 3 0.0364 nan 0.0100 0.0005
## 4 0.0361 nan 0.0100 0.0003
## 5 0.0357 nan 0.0100 0.0004
## 6 0.0352 nan 0.0100 0.0005
## 7 0.0348 nan 0.0100 0.0002
## 8 0.0345 nan 0.0100 0.0001
## 9 0.0342 nan 0.0100 0.0001
## 10 0.0339 nan 0.0100 0.0004
## 20 0.0304 nan 0.0100 0.0004
## 40 0.0244 nan 0.0100 0.0002
## 60 0.0198 nan 0.0100 0.0002
## 80 0.0168 nan 0.0100 0.0001
## 100 0.0142 nan 0.0100 0.0000
## 120 0.0122 nan 0.0100 0.0001
## 140 0.0104 nan 0.0100 0.0001
## 160 0.0092 nan 0.0100 0.0000
## 180 0.0083 nan 0.0100 0.0000
## 200 0.0074 nan 0.0100 -0.0000
##
## - Fold03: shrinkage=0.01, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold03: shrinkage=0.05, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0354 nan 0.0500 0.0018
## 2 0.0332 nan 0.0500 0.0014
## 3 0.0314 nan 0.0500 0.0010
## 4 0.0294 nan 0.0500 0.0015
## 5 0.0272 nan 0.0500 0.0016
## 6 0.0251 nan 0.0500 0.0015
## 7 0.0236 nan 0.0500 0.0009
## 8 0.0227 nan 0.0500 0.0008
## 9 0.0216 nan 0.0500 0.0006
## 10 0.0202 nan 0.0500 0.0014
## 20 0.0128 nan 0.0500 -0.0001
## 40 0.0053 nan 0.0500 0.0001
## 60 0.0026 nan 0.0500 0.0001
## 80 0.0015 nan 0.0500 0.0000
## 100 0.0009 nan 0.0500 -0.0000
## 120 0.0006 nan 0.0500 0.0000
## 140 0.0003 nan 0.0500 -0.0000
## 160 0.0002 nan 0.0500 0.0000
## 180 0.0001 nan 0.0500 -0.0000
## 200 0.0001 nan 0.0500 -0.0000
##
## - Fold03: shrinkage=0.05, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold03: shrinkage=0.05, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0353 nan 0.0500 0.0016
## 2 0.0336 nan 0.0500 0.0016
## 3 0.0324 nan 0.0500 0.0004
## 4 0.0302 nan 0.0500 0.0017
## 5 0.0278 nan 0.0500 0.0018
## 6 0.0259 nan 0.0500 0.0016
## 7 0.0244 nan 0.0500 0.0015
## 8 0.0230 nan 0.0500 0.0010
## 9 0.0216 nan 0.0500 0.0014
## 10 0.0211 nan 0.0500 -0.0007
## 20 0.0135 nan 0.0500 -0.0002
## 40 0.0062 nan 0.0500 0.0001
## 60 0.0028 nan 0.0500 0.0000
## 80 0.0016 nan 0.0500 -0.0000
## 100 0.0010 nan 0.0500 -0.0000
## 120 0.0006 nan 0.0500 -0.0000
## 140 0.0005 nan 0.0500 -0.0000
## 160 0.0003 nan 0.0500 -0.0000
## 180 0.0002 nan 0.0500 -0.0000
## 200 0.0001 nan 0.0500 -0.0000
##
## - Fold03: shrinkage=0.05, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold03: shrinkage=0.05, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0355 nan 0.0500 0.0004
## 2 0.0327 nan 0.0500 0.0025
## 3 0.0305 nan 0.0500 0.0017
## 4 0.0283 nan 0.0500 0.0015
## 5 0.0273 nan 0.0500 0.0007
## 6 0.0255 nan 0.0500 0.0014
## 7 0.0243 nan 0.0500 0.0012
## 8 0.0228 nan 0.0500 0.0010
## 9 0.0213 nan 0.0500 0.0013
## 10 0.0202 nan 0.0500 0.0010
## 20 0.0128 nan 0.0500 0.0005
## 40 0.0072 nan 0.0500 -0.0002
## 60 0.0049 nan 0.0500 -0.0000
## 80 0.0033 nan 0.0500 -0.0001
## 100 0.0025 nan 0.0500 -0.0000
## 120 0.0018 nan 0.0500 -0.0000
## 140 0.0014 nan 0.0500 -0.0000
## 160 0.0011 nan 0.0500 -0.0000
## 180 0.0008 nan 0.0500 0.0000
## 200 0.0006 nan 0.0500 -0.0000
##
## - Fold03: shrinkage=0.05, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold03: shrinkage=0.05, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0348 nan 0.0500 0.0021
## 2 0.0322 nan 0.0500 0.0016
## 3 0.0299 nan 0.0500 0.0022
## 4 0.0280 nan 0.0500 0.0008
## 5 0.0268 nan 0.0500 0.0003
## 6 0.0250 nan 0.0500 0.0016
## 7 0.0230 nan 0.0500 0.0018
## 8 0.0209 nan 0.0500 0.0017
## 9 0.0190 nan 0.0500 0.0012
## 10 0.0182 nan 0.0500 0.0009
## 20 0.0103 nan 0.0500 0.0004
## 40 0.0032 nan 0.0500 0.0001
## 60 0.0012 nan 0.0500 0.0000
## 80 0.0006 nan 0.0500 -0.0000
## 100 0.0003 nan 0.0500 -0.0000
## 120 0.0002 nan 0.0500 0.0000
## 140 0.0001 nan 0.0500 -0.0000
## 160 0.0001 nan 0.0500 -0.0000
## 180 0.0000 nan 0.0500 -0.0000
## 200 0.0000 nan 0.0500 -0.0000
##
## - Fold03: shrinkage=0.05, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold03: shrinkage=0.05, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0339 nan 0.0500 0.0026
## 2 0.0314 nan 0.0500 0.0004
## 3 0.0290 nan 0.0500 0.0006
## 4 0.0265 nan 0.0500 0.0022
## 5 0.0249 nan 0.0500 0.0018
## 6 0.0232 nan 0.0500 0.0013
## 7 0.0224 nan 0.0500 0.0007
## 8 0.0216 nan 0.0500 0.0005
## 9 0.0201 nan 0.0500 0.0014
## 10 0.0188 nan 0.0500 0.0010
## 20 0.0111 nan 0.0500 0.0000
## 40 0.0042 nan 0.0500 0.0001
## 60 0.0020 nan 0.0500 0.0000
## 80 0.0010 nan 0.0500 -0.0000
## 100 0.0007 nan 0.0500 -0.0000
## 120 0.0004 nan 0.0500 -0.0000
## 140 0.0003 nan 0.0500 -0.0000
## 160 0.0002 nan 0.0500 -0.0000
## 180 0.0001 nan 0.0500 -0.0000
## 200 0.0001 nan 0.0500 -0.0000
##
## - Fold03: shrinkage=0.05, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold03: shrinkage=0.05, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0350 nan 0.0500 0.0024
## 2 0.0331 nan 0.0500 0.0021
## 3 0.0308 nan 0.0500 0.0023
## 4 0.0296 nan 0.0500 -0.0009
## 5 0.0281 nan 0.0500 0.0017
## 6 0.0266 nan 0.0500 0.0010
## 7 0.0253 nan 0.0500 0.0007
## 8 0.0234 nan 0.0500 0.0017
## 9 0.0223 nan 0.0500 0.0011
## 10 0.0215 nan 0.0500 0.0008
## 20 0.0137 nan 0.0500 0.0003
## 40 0.0071 nan 0.0500 0.0002
## 60 0.0044 nan 0.0500 0.0001
## 80 0.0030 nan 0.0500 -0.0001
## 100 0.0023 nan 0.0500 0.0000
## 120 0.0017 nan 0.0500 0.0000
## 140 0.0012 nan 0.0500 -0.0000
## 160 0.0010 nan 0.0500 0.0000
## 180 0.0007 nan 0.0500 -0.0000
## 200 0.0005 nan 0.0500 0.0000
##
## - Fold03: shrinkage=0.05, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold03: shrinkage=0.05, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0346 nan 0.0500 0.0019
## 2 0.0319 nan 0.0500 0.0027
## 3 0.0300 nan 0.0500 0.0019
## 4 0.0272 nan 0.0500 0.0019
## 5 0.0249 nan 0.0500 0.0021
## 6 0.0237 nan 0.0500 0.0010
## 7 0.0225 nan 0.0500 0.0014
## 8 0.0203 nan 0.0500 0.0022
## 9 0.0189 nan 0.0500 0.0013
## 10 0.0177 nan 0.0500 0.0003
## 20 0.0092 nan 0.0500 0.0007
## 40 0.0028 nan 0.0500 0.0000
## 60 0.0009 nan 0.0500 -0.0000
## 80 0.0004 nan 0.0500 -0.0000
## 100 0.0002 nan 0.0500 0.0000
## 120 0.0001 nan 0.0500 -0.0000
## 140 0.0000 nan 0.0500 -0.0000
## 160 0.0000 nan 0.0500 -0.0000
## 180 0.0000 nan 0.0500 -0.0000
## 200 0.0000 nan 0.0500 -0.0000
##
## - Fold03: shrinkage=0.05, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold03: shrinkage=0.05, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0347 nan 0.0500 0.0030
## 2 0.0319 nan 0.0500 0.0024
## 3 0.0291 nan 0.0500 0.0025
## 4 0.0267 nan 0.0500 0.0022
## 5 0.0242 nan 0.0500 0.0016
## 6 0.0228 nan 0.0500 0.0011
## 7 0.0211 nan 0.0500 0.0013
## 8 0.0197 nan 0.0500 0.0011
## 9 0.0187 nan 0.0500 0.0003
## 10 0.0170 nan 0.0500 0.0013
## 20 0.0094 nan 0.0500 0.0005
## 40 0.0032 nan 0.0500 0.0001
## 60 0.0014 nan 0.0500 -0.0000
## 80 0.0009 nan 0.0500 -0.0000
## 100 0.0005 nan 0.0500 -0.0000
## 120 0.0003 nan 0.0500 -0.0000
## 140 0.0002 nan 0.0500 0.0000
## 160 0.0001 nan 0.0500 -0.0000
## 180 0.0001 nan 0.0500 0.0000
## 200 0.0001 nan 0.0500 0.0000
##
## - Fold03: shrinkage=0.05, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold03: shrinkage=0.05, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0347 nan 0.0500 0.0026
## 2 0.0334 nan 0.0500 0.0008
## 3 0.0312 nan 0.0500 0.0022
## 4 0.0292 nan 0.0500 0.0018
## 5 0.0275 nan 0.0500 0.0017
## 6 0.0262 nan 0.0500 0.0011
## 7 0.0251 nan 0.0500 0.0002
## 8 0.0241 nan 0.0500 0.0007
## 9 0.0228 nan 0.0500 0.0011
## 10 0.0215 nan 0.0500 0.0013
## 20 0.0133 nan 0.0500 0.0003
## 40 0.0070 nan 0.0500 0.0002
## 60 0.0046 nan 0.0500 -0.0000
## 80 0.0034 nan 0.0500 -0.0001
## 100 0.0022 nan 0.0500 -0.0000
## 120 0.0018 nan 0.0500 -0.0000
## 140 0.0012 nan 0.0500 -0.0000
## 160 0.0009 nan 0.0500 -0.0000
## 180 0.0008 nan 0.0500 0.0000
## 200 0.0006 nan 0.0500 -0.0000
##
## - Fold03: shrinkage=0.05, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold03: shrinkage=0.10, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0338 nan 0.1000 0.0024
## 2 0.0290 nan 0.1000 0.0049
## 3 0.0268 nan 0.1000 0.0010
## 4 0.0252 nan 0.1000 0.0001
## 5 0.0225 nan 0.1000 0.0026
## 6 0.0219 nan 0.1000 -0.0018
## 7 0.0195 nan 0.1000 0.0026
## 8 0.0178 nan 0.1000 0.0013
## 9 0.0154 nan 0.1000 0.0016
## 10 0.0147 nan 0.1000 -0.0005
## 20 0.0068 nan 0.1000 0.0004
## 40 0.0016 nan 0.1000 0.0002
## 60 0.0005 nan 0.1000 0.0000
## 80 0.0002 nan 0.1000 -0.0000
## 100 0.0001 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold03: shrinkage=0.10, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold03: shrinkage=0.10, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0329 nan 0.1000 0.0036
## 2 0.0291 nan 0.1000 0.0039
## 3 0.0266 nan 0.1000 0.0026
## 4 0.0257 nan 0.1000 -0.0000
## 5 0.0224 nan 0.1000 0.0023
## 6 0.0211 nan 0.1000 0.0013
## 7 0.0182 nan 0.1000 0.0012
## 8 0.0172 nan 0.1000 -0.0002
## 9 0.0153 nan 0.1000 0.0005
## 10 0.0132 nan 0.1000 0.0013
## 20 0.0062 nan 0.1000 0.0004
## 40 0.0022 nan 0.1000 -0.0000
## 60 0.0011 nan 0.1000 -0.0000
## 80 0.0005 nan 0.1000 -0.0000
## 100 0.0003 nan 0.1000 0.0000
## 120 0.0001 nan 0.1000 -0.0000
## 140 0.0001 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold03: shrinkage=0.10, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold03: shrinkage=0.10, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0329 nan 0.1000 0.0046
## 2 0.0296 nan 0.1000 0.0021
## 3 0.0264 nan 0.1000 0.0010
## 4 0.0241 nan 0.1000 0.0015
## 5 0.0224 nan 0.1000 0.0014
## 6 0.0204 nan 0.1000 0.0016
## 7 0.0194 nan 0.1000 0.0004
## 8 0.0183 nan 0.1000 0.0008
## 9 0.0175 nan 0.1000 -0.0006
## 10 0.0160 nan 0.1000 0.0010
## 20 0.0088 nan 0.1000 -0.0001
## 40 0.0038 nan 0.1000 -0.0001
## 60 0.0019 nan 0.1000 0.0000
## 80 0.0011 nan 0.1000 -0.0001
## 100 0.0006 nan 0.1000 0.0000
## 120 0.0004 nan 0.1000 -0.0000
## 140 0.0002 nan 0.1000 0.0000
## 160 0.0002 nan 0.1000 0.0000
## 180 0.0001 nan 0.1000 -0.0000
## 200 0.0001 nan 0.1000 -0.0000
##
## - Fold03: shrinkage=0.10, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold03: shrinkage=0.10, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0332 nan 0.1000 0.0015
## 2 0.0301 nan 0.1000 0.0000
## 3 0.0262 nan 0.1000 0.0044
## 4 0.0233 nan 0.1000 0.0030
## 5 0.0201 nan 0.1000 0.0026
## 6 0.0184 nan 0.1000 -0.0004
## 7 0.0175 nan 0.1000 0.0002
## 8 0.0159 nan 0.1000 0.0002
## 9 0.0134 nan 0.1000 0.0020
## 10 0.0123 nan 0.1000 0.0007
## 20 0.0038 nan 0.1000 0.0001
## 40 0.0006 nan 0.1000 -0.0000
## 60 0.0002 nan 0.1000 -0.0000
## 80 0.0000 nan 0.1000 -0.0000
## 100 0.0000 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold03: shrinkage=0.10, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold03: shrinkage=0.10, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0311 nan 0.1000 0.0038
## 2 0.0282 nan 0.1000 0.0028
## 3 0.0246 nan 0.1000 0.0019
## 4 0.0222 nan 0.1000 0.0022
## 5 0.0203 nan 0.1000 0.0014
## 6 0.0172 nan 0.1000 0.0023
## 7 0.0147 nan 0.1000 0.0012
## 8 0.0127 nan 0.1000 0.0010
## 9 0.0106 nan 0.1000 0.0013
## 10 0.0095 nan 0.1000 0.0002
## 20 0.0042 nan 0.1000 -0.0000
## 40 0.0008 nan 0.1000 0.0000
## 60 0.0002 nan 0.1000 0.0000
## 80 0.0001 nan 0.1000 -0.0000
## 100 0.0000 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold03: shrinkage=0.10, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold03: shrinkage=0.10, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0332 nan 0.1000 0.0037
## 2 0.0290 nan 0.1000 0.0040
## 3 0.0250 nan 0.1000 0.0037
## 4 0.0224 nan 0.1000 0.0028
## 5 0.0217 nan 0.1000 -0.0007
## 6 0.0202 nan 0.1000 0.0012
## 7 0.0195 nan 0.1000 -0.0013
## 8 0.0167 nan 0.1000 0.0014
## 9 0.0155 nan 0.1000 0.0008
## 10 0.0147 nan 0.1000 0.0009
## 20 0.0081 nan 0.1000 0.0002
## 40 0.0034 nan 0.1000 0.0000
## 60 0.0018 nan 0.1000 -0.0001
## 80 0.0009 nan 0.1000 -0.0000
## 100 0.0005 nan 0.1000 -0.0000
## 120 0.0003 nan 0.1000 -0.0000
## 140 0.0002 nan 0.1000 -0.0000
## 160 0.0001 nan 0.1000 0.0000
## 180 0.0001 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold03: shrinkage=0.10, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold03: shrinkage=0.10, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0314 nan 0.1000 0.0054
## 2 0.0273 nan 0.1000 0.0012
## 3 0.0221 nan 0.1000 0.0047
## 4 0.0197 nan 0.1000 0.0005
## 5 0.0163 nan 0.1000 0.0027
## 6 0.0143 nan 0.1000 0.0010
## 7 0.0125 nan 0.1000 0.0011
## 8 0.0111 nan 0.1000 0.0011
## 9 0.0098 nan 0.1000 -0.0000
## 10 0.0089 nan 0.1000 0.0003
## 20 0.0025 nan 0.1000 0.0001
## 40 0.0003 nan 0.1000 -0.0000
## 60 0.0001 nan 0.1000 -0.0000
## 80 0.0000 nan 0.1000 0.0000
## 100 0.0000 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold03: shrinkage=0.10, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold03: shrinkage=0.10, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0336 nan 0.1000 0.0013
## 2 0.0301 nan 0.1000 0.0040
## 3 0.0264 nan 0.1000 0.0041
## 4 0.0241 nan 0.1000 0.0017
## 5 0.0211 nan 0.1000 0.0019
## 6 0.0190 nan 0.1000 0.0008
## 7 0.0174 nan 0.1000 0.0001
## 8 0.0156 nan 0.1000 -0.0000
## 9 0.0139 nan 0.1000 0.0022
## 10 0.0126 nan 0.1000 0.0015
## 20 0.0050 nan 0.1000 -0.0001
## 40 0.0013 nan 0.1000 0.0000
## 60 0.0006 nan 0.1000 0.0000
## 80 0.0002 nan 0.1000 -0.0000
## 100 0.0001 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold03: shrinkage=0.10, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold03: shrinkage=0.10, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0334 nan 0.1000 0.0040
## 2 0.0297 nan 0.1000 0.0035
## 3 0.0266 nan 0.1000 0.0014
## 4 0.0245 nan 0.1000 0.0023
## 5 0.0215 nan 0.1000 0.0011
## 6 0.0190 nan 0.1000 0.0019
## 7 0.0167 nan 0.1000 0.0021
## 8 0.0157 nan 0.1000 0.0003
## 9 0.0140 nan 0.1000 0.0008
## 10 0.0127 nan 0.1000 0.0008
## 20 0.0067 nan 0.1000 0.0003
## 40 0.0030 nan 0.1000 0.0001
## 60 0.0020 nan 0.1000 -0.0001
## 80 0.0012 nan 0.1000 -0.0000
## 100 0.0007 nan 0.1000 0.0000
## 120 0.0004 nan 0.1000 -0.0000
## 140 0.0003 nan 0.1000 0.0000
## 160 0.0002 nan 0.1000 0.0000
## 180 0.0001 nan 0.1000 -0.0000
## 200 0.0001 nan 0.1000 -0.0000
##
## - Fold03: shrinkage=0.10, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold04: shrinkage=0.01, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0438 nan 0.0100 0.0005
## 2 0.0432 nan 0.0100 0.0006
## 3 0.0429 nan 0.0100 0.0002
## 4 0.0421 nan 0.0100 0.0006
## 5 0.0417 nan 0.0100 0.0001
## 6 0.0416 nan 0.0100 -0.0002
## 7 0.0413 nan 0.0100 0.0001
## 8 0.0408 nan 0.0100 0.0005
## 9 0.0401 nan 0.0100 0.0006
## 10 0.0396 nan 0.0100 0.0004
## 20 0.0348 nan 0.0100 0.0004
## 40 0.0276 nan 0.0100 0.0002
## 60 0.0221 nan 0.0100 -0.0000
## 80 0.0180 nan 0.0100 0.0001
## 100 0.0146 nan 0.0100 0.0001
## 120 0.0123 nan 0.0100 0.0001
## 140 0.0104 nan 0.0100 0.0001
## 160 0.0087 nan 0.0100 0.0000
## 180 0.0074 nan 0.0100 0.0000
## 200 0.0062 nan 0.0100 0.0000
##
## - Fold04: shrinkage=0.01, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold04: shrinkage=0.01, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0439 nan 0.0100 0.0002
## 2 0.0433 nan 0.0100 0.0006
## 3 0.0426 nan 0.0100 0.0005
## 4 0.0420 nan 0.0100 0.0005
## 5 0.0415 nan 0.0100 0.0003
## 6 0.0409 nan 0.0100 0.0005
## 7 0.0403 nan 0.0100 0.0002
## 8 0.0397 nan 0.0100 0.0002
## 9 0.0395 nan 0.0100 -0.0001
## 10 0.0391 nan 0.0100 0.0001
## 20 0.0346 nan 0.0100 0.0005
## 40 0.0279 nan 0.0100 0.0004
## 60 0.0224 nan 0.0100 0.0000
## 80 0.0184 nan 0.0100 0.0002
## 100 0.0150 nan 0.0100 0.0002
## 120 0.0124 nan 0.0100 0.0001
## 140 0.0104 nan 0.0100 0.0000
## 160 0.0088 nan 0.0100 0.0000
## 180 0.0074 nan 0.0100 0.0000
## 200 0.0062 nan 0.0100 0.0000
##
## - Fold04: shrinkage=0.01, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold04: shrinkage=0.01, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0439 nan 0.0100 0.0003
## 2 0.0434 nan 0.0100 0.0005
## 3 0.0430 nan 0.0100 0.0002
## 4 0.0426 nan 0.0100 0.0003
## 5 0.0421 nan 0.0100 0.0002
## 6 0.0415 nan 0.0100 0.0005
## 7 0.0409 nan 0.0100 0.0006
## 8 0.0405 nan 0.0100 0.0004
## 9 0.0399 nan 0.0100 0.0006
## 10 0.0396 nan 0.0100 0.0002
## 20 0.0355 nan 0.0100 0.0004
## 40 0.0285 nan 0.0100 0.0003
## 60 0.0226 nan 0.0100 0.0002
## 80 0.0188 nan 0.0100 0.0002
## 100 0.0156 nan 0.0100 0.0001
## 120 0.0131 nan 0.0100 0.0001
## 140 0.0115 nan 0.0100 0.0000
## 160 0.0101 nan 0.0100 0.0000
## 180 0.0089 nan 0.0100 0.0000
## 200 0.0080 nan 0.0100 -0.0000
##
## - Fold04: shrinkage=0.01, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold04: shrinkage=0.01, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0441 nan 0.0100 0.0002
## 2 0.0432 nan 0.0100 0.0005
## 3 0.0426 nan 0.0100 0.0006
## 4 0.0422 nan 0.0100 0.0002
## 5 0.0416 nan 0.0100 0.0005
## 6 0.0408 nan 0.0100 0.0008
## 7 0.0402 nan 0.0100 0.0005
## 8 0.0395 nan 0.0100 0.0005
## 9 0.0390 nan 0.0100 0.0005
## 10 0.0384 nan 0.0100 0.0004
## 20 0.0335 nan 0.0100 0.0003
## 40 0.0252 nan 0.0100 0.0004
## 60 0.0188 nan 0.0100 0.0002
## 80 0.0142 nan 0.0100 0.0001
## 100 0.0112 nan 0.0100 0.0001
## 120 0.0088 nan 0.0100 0.0001
## 140 0.0070 nan 0.0100 0.0000
## 160 0.0056 nan 0.0100 0.0000
## 180 0.0044 nan 0.0100 0.0000
## 200 0.0035 nan 0.0100 -0.0000
##
## - Fold04: shrinkage=0.01, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold04: shrinkage=0.01, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0438 nan 0.0100 0.0005
## 2 0.0432 nan 0.0100 0.0006
## 3 0.0425 nan 0.0100 0.0005
## 4 0.0422 nan 0.0100 0.0003
## 5 0.0415 nan 0.0100 0.0007
## 6 0.0407 nan 0.0100 0.0005
## 7 0.0402 nan 0.0100 0.0004
## 8 0.0399 nan 0.0100 -0.0001
## 9 0.0393 nan 0.0100 0.0005
## 10 0.0387 nan 0.0100 0.0003
## 20 0.0338 nan 0.0100 0.0002
## 40 0.0259 nan 0.0100 0.0002
## 60 0.0199 nan 0.0100 0.0001
## 80 0.0160 nan 0.0100 0.0002
## 100 0.0128 nan 0.0100 0.0002
## 120 0.0101 nan 0.0100 0.0000
## 140 0.0082 nan 0.0100 0.0001
## 160 0.0066 nan 0.0100 -0.0000
## 180 0.0054 nan 0.0100 0.0000
## 200 0.0045 nan 0.0100 0.0000
##
## - Fold04: shrinkage=0.01, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold04: shrinkage=0.01, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0437 nan 0.0100 0.0005
## 2 0.0431 nan 0.0100 0.0006
## 3 0.0426 nan 0.0100 0.0003
## 4 0.0421 nan 0.0100 0.0004
## 5 0.0415 nan 0.0100 0.0005
## 6 0.0412 nan 0.0100 0.0002
## 7 0.0408 nan 0.0100 0.0003
## 8 0.0403 nan 0.0100 0.0005
## 9 0.0400 nan 0.0100 0.0002
## 10 0.0396 nan 0.0100 0.0003
## 20 0.0355 nan 0.0100 0.0004
## 40 0.0283 nan 0.0100 0.0002
## 60 0.0231 nan 0.0100 0.0003
## 80 0.0193 nan 0.0100 0.0002
## 100 0.0162 nan 0.0100 0.0001
## 120 0.0142 nan 0.0100 0.0000
## 140 0.0122 nan 0.0100 -0.0000
## 160 0.0104 nan 0.0100 0.0000
## 180 0.0091 nan 0.0100 0.0000
## 200 0.0082 nan 0.0100 0.0000
##
## - Fold04: shrinkage=0.01, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold04: shrinkage=0.01, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0437 nan 0.0100 0.0006
## 2 0.0431 nan 0.0100 0.0003
## 3 0.0423 nan 0.0100 0.0005
## 4 0.0416 nan 0.0100 0.0009
## 5 0.0409 nan 0.0100 0.0004
## 6 0.0405 nan 0.0100 -0.0001
## 7 0.0399 nan 0.0100 0.0003
## 8 0.0393 nan 0.0100 0.0004
## 9 0.0387 nan 0.0100 0.0005
## 10 0.0381 nan 0.0100 0.0005
## 20 0.0329 nan 0.0100 0.0004
## 40 0.0249 nan 0.0100 0.0002
## 60 0.0188 nan 0.0100 -0.0000
## 80 0.0143 nan 0.0100 0.0002
## 100 0.0109 nan 0.0100 0.0001
## 120 0.0085 nan 0.0100 0.0000
## 140 0.0069 nan 0.0100 0.0000
## 160 0.0054 nan 0.0100 -0.0000
## 180 0.0042 nan 0.0100 0.0000
## 200 0.0034 nan 0.0100 0.0000
##
## - Fold04: shrinkage=0.01, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold04: shrinkage=0.01, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0438 nan 0.0100 0.0006
## 2 0.0433 nan 0.0100 0.0005
## 3 0.0427 nan 0.0100 0.0005
## 4 0.0419 nan 0.0100 0.0005
## 5 0.0413 nan 0.0100 0.0005
## 6 0.0405 nan 0.0100 0.0006
## 7 0.0399 nan 0.0100 0.0004
## 8 0.0395 nan 0.0100 0.0003
## 9 0.0389 nan 0.0100 0.0002
## 10 0.0383 nan 0.0100 0.0006
## 20 0.0333 nan 0.0100 0.0005
## 40 0.0259 nan 0.0100 0.0002
## 60 0.0201 nan 0.0100 0.0002
## 80 0.0155 nan 0.0100 0.0001
## 100 0.0121 nan 0.0100 0.0001
## 120 0.0096 nan 0.0100 0.0001
## 140 0.0079 nan 0.0100 -0.0000
## 160 0.0063 nan 0.0100 0.0000
## 180 0.0050 nan 0.0100 0.0000
## 200 0.0040 nan 0.0100 0.0000
##
## - Fold04: shrinkage=0.01, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold04: shrinkage=0.01, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0437 nan 0.0100 0.0006
## 2 0.0431 nan 0.0100 0.0005
## 3 0.0425 nan 0.0100 0.0002
## 4 0.0419 nan 0.0100 0.0005
## 5 0.0416 nan 0.0100 0.0002
## 6 0.0412 nan 0.0100 0.0005
## 7 0.0408 nan 0.0100 0.0003
## 8 0.0402 nan 0.0100 0.0005
## 9 0.0398 nan 0.0100 0.0003
## 10 0.0393 nan 0.0100 0.0002
## 20 0.0350 nan 0.0100 0.0004
## 40 0.0282 nan 0.0100 0.0001
## 60 0.0222 nan 0.0100 0.0001
## 80 0.0182 nan 0.0100 0.0001
## 100 0.0155 nan 0.0100 0.0001
## 120 0.0133 nan 0.0100 0.0001
## 140 0.0114 nan 0.0100 0.0000
## 160 0.0101 nan 0.0100 0.0000
## 180 0.0089 nan 0.0100 -0.0000
## 200 0.0078 nan 0.0100 0.0001
##
## - Fold04: shrinkage=0.01, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold04: shrinkage=0.05, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0407 nan 0.0500 0.0034
## 2 0.0384 nan 0.0500 0.0019
## 3 0.0359 nan 0.0500 0.0023
## 4 0.0337 nan 0.0500 0.0020
## 5 0.0314 nan 0.0500 0.0015
## 6 0.0289 nan 0.0500 0.0015
## 7 0.0270 nan 0.0500 0.0007
## 8 0.0255 nan 0.0500 0.0010
## 9 0.0246 nan 0.0500 0.0001
## 10 0.0231 nan 0.0500 0.0013
## 20 0.0138 nan 0.0500 0.0001
## 40 0.0059 nan 0.0500 0.0003
## 60 0.0029 nan 0.0500 -0.0000
## 80 0.0015 nan 0.0500 0.0000
## 100 0.0009 nan 0.0500 -0.0000
## 120 0.0006 nan 0.0500 0.0000
## 140 0.0004 nan 0.0500 -0.0000
## 160 0.0002 nan 0.0500 0.0000
## 180 0.0001 nan 0.0500 -0.0000
## 200 0.0001 nan 0.0500 0.0000
##
## - Fold04: shrinkage=0.05, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold04: shrinkage=0.05, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0431 nan 0.0500 0.0010
## 2 0.0401 nan 0.0500 0.0031
## 3 0.0368 nan 0.0500 0.0030
## 4 0.0344 nan 0.0500 0.0019
## 5 0.0320 nan 0.0500 0.0011
## 6 0.0298 nan 0.0500 0.0010
## 7 0.0282 nan 0.0500 -0.0000
## 8 0.0262 nan 0.0500 0.0012
## 9 0.0246 nan 0.0500 0.0010
## 10 0.0235 nan 0.0500 0.0009
## 20 0.0140 nan 0.0500 0.0006
## 40 0.0064 nan 0.0500 -0.0000
## 60 0.0033 nan 0.0500 0.0001
## 80 0.0017 nan 0.0500 -0.0000
## 100 0.0010 nan 0.0500 0.0000
## 120 0.0006 nan 0.0500 -0.0000
## 140 0.0004 nan 0.0500 0.0000
## 160 0.0003 nan 0.0500 0.0000
## 180 0.0002 nan 0.0500 -0.0000
## 200 0.0001 nan 0.0500 -0.0000
##
## - Fold04: shrinkage=0.05, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold04: shrinkage=0.05, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0418 nan 0.0500 0.0023
## 2 0.0392 nan 0.0500 0.0018
## 3 0.0368 nan 0.0500 0.0026
## 4 0.0347 nan 0.0500 0.0020
## 5 0.0329 nan 0.0500 0.0021
## 6 0.0308 nan 0.0500 0.0020
## 7 0.0286 nan 0.0500 0.0011
## 8 0.0269 nan 0.0500 0.0014
## 9 0.0265 nan 0.0500 -0.0008
## 10 0.0252 nan 0.0500 0.0012
## 20 0.0160 nan 0.0500 0.0006
## 40 0.0078 nan 0.0500 0.0001
## 60 0.0047 nan 0.0500 0.0000
## 80 0.0034 nan 0.0500 -0.0000
## 100 0.0024 nan 0.0500 -0.0001
## 120 0.0017 nan 0.0500 -0.0000
## 140 0.0013 nan 0.0500 0.0000
## 160 0.0009 nan 0.0500 -0.0000
## 180 0.0007 nan 0.0500 -0.0000
## 200 0.0006 nan 0.0500 -0.0000
##
## - Fold04: shrinkage=0.05, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold04: shrinkage=0.05, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0417 nan 0.0500 0.0016
## 2 0.0394 nan 0.0500 0.0011
## 3 0.0375 nan 0.0500 0.0006
## 4 0.0354 nan 0.0500 0.0005
## 5 0.0321 nan 0.0500 0.0014
## 6 0.0295 nan 0.0500 0.0025
## 7 0.0280 nan 0.0500 0.0003
## 8 0.0262 nan 0.0500 0.0015
## 9 0.0241 nan 0.0500 0.0012
## 10 0.0228 nan 0.0500 0.0014
## 20 0.0118 nan 0.0500 0.0003
## 40 0.0040 nan 0.0500 0.0001
## 60 0.0017 nan 0.0500 0.0000
## 80 0.0008 nan 0.0500 0.0000
## 100 0.0004 nan 0.0500 0.0000
## 120 0.0002 nan 0.0500 -0.0000
## 140 0.0001 nan 0.0500 -0.0000
## 160 0.0001 nan 0.0500 -0.0000
## 180 0.0000 nan 0.0500 0.0000
## 200 0.0000 nan 0.0500 -0.0000
##
## - Fold04: shrinkage=0.05, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold04: shrinkage=0.05, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0411 nan 0.0500 0.0029
## 2 0.0384 nan 0.0500 0.0019
## 3 0.0369 nan 0.0500 0.0012
## 4 0.0346 nan 0.0500 0.0019
## 5 0.0323 nan 0.0500 0.0021
## 6 0.0299 nan 0.0500 0.0025
## 7 0.0275 nan 0.0500 0.0018
## 8 0.0262 nan 0.0500 0.0007
## 9 0.0250 nan 0.0500 0.0014
## 10 0.0232 nan 0.0500 0.0007
## 20 0.0123 nan 0.0500 0.0005
## 40 0.0044 nan 0.0500 0.0000
## 60 0.0021 nan 0.0500 -0.0000
## 80 0.0010 nan 0.0500 -0.0000
## 100 0.0005 nan 0.0500 0.0000
## 120 0.0003 nan 0.0500 -0.0000
## 140 0.0002 nan 0.0500 -0.0000
## 160 0.0001 nan 0.0500 -0.0000
## 180 0.0001 nan 0.0500 -0.0000
## 200 0.0000 nan 0.0500 0.0000
##
## - Fold04: shrinkage=0.05, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold04: shrinkage=0.05, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0432 nan 0.0500 0.0006
## 2 0.0401 nan 0.0500 0.0030
## 3 0.0376 nan 0.0500 0.0027
## 4 0.0353 nan 0.0500 0.0010
## 5 0.0331 nan 0.0500 0.0020
## 6 0.0312 nan 0.0500 0.0007
## 7 0.0300 nan 0.0500 0.0003
## 8 0.0287 nan 0.0500 0.0007
## 9 0.0270 nan 0.0500 0.0017
## 10 0.0259 nan 0.0500 0.0007
## 20 0.0165 nan 0.0500 -0.0002
## 40 0.0084 nan 0.0500 0.0002
## 60 0.0061 nan 0.0500 0.0001
## 80 0.0042 nan 0.0500 -0.0001
## 100 0.0029 nan 0.0500 0.0000
## 120 0.0020 nan 0.0500 -0.0000
## 140 0.0015 nan 0.0500 -0.0000
## 160 0.0011 nan 0.0500 -0.0000
## 180 0.0009 nan 0.0500 -0.0000
## 200 0.0007 nan 0.0500 -0.0000
##
## - Fold04: shrinkage=0.05, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold04: shrinkage=0.05, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0410 nan 0.0500 0.0023
## 2 0.0383 nan 0.0500 0.0022
## 3 0.0357 nan 0.0500 0.0021
## 4 0.0326 nan 0.0500 0.0018
## 5 0.0311 nan 0.0500 0.0009
## 6 0.0293 nan 0.0500 0.0003
## 7 0.0280 nan 0.0500 0.0003
## 8 0.0260 nan 0.0500 0.0013
## 9 0.0247 nan 0.0500 0.0016
## 10 0.0237 nan 0.0500 0.0007
## 20 0.0127 nan 0.0500 0.0001
## 40 0.0039 nan 0.0500 -0.0001
## 60 0.0017 nan 0.0500 0.0000
## 80 0.0007 nan 0.0500 -0.0000
## 100 0.0003 nan 0.0500 0.0000
## 120 0.0001 nan 0.0500 -0.0000
## 140 0.0001 nan 0.0500 -0.0000
## 160 0.0000 nan 0.0500 0.0000
## 180 0.0000 nan 0.0500 -0.0000
## 200 0.0000 nan 0.0500 -0.0000
##
## - Fold04: shrinkage=0.05, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold04: shrinkage=0.05, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0407 nan 0.0500 0.0031
## 2 0.0374 nan 0.0500 0.0030
## 3 0.0355 nan 0.0500 0.0007
## 4 0.0335 nan 0.0500 0.0018
## 5 0.0312 nan 0.0500 0.0016
## 6 0.0283 nan 0.0500 0.0026
## 7 0.0266 nan 0.0500 0.0011
## 8 0.0254 nan 0.0500 0.0012
## 9 0.0236 nan 0.0500 0.0019
## 10 0.0224 nan 0.0500 0.0008
## 20 0.0122 nan 0.0500 0.0005
## 40 0.0043 nan 0.0500 0.0000
## 60 0.0018 nan 0.0500 0.0000
## 80 0.0009 nan 0.0500 -0.0000
## 100 0.0005 nan 0.0500 -0.0000
## 120 0.0003 nan 0.0500 0.0000
## 140 0.0002 nan 0.0500 -0.0000
## 160 0.0001 nan 0.0500 -0.0000
## 180 0.0001 nan 0.0500 -0.0000
## 200 0.0001 nan 0.0500 -0.0000
##
## - Fold04: shrinkage=0.05, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold04: shrinkage=0.05, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0421 nan 0.0500 0.0018
## 2 0.0396 nan 0.0500 0.0022
## 3 0.0364 nan 0.0500 0.0024
## 4 0.0339 nan 0.0500 0.0023
## 5 0.0318 nan 0.0500 0.0013
## 6 0.0302 nan 0.0500 0.0018
## 7 0.0283 nan 0.0500 0.0014
## 8 0.0270 nan 0.0500 0.0011
## 9 0.0257 nan 0.0500 0.0006
## 10 0.0247 nan 0.0500 0.0010
## 20 0.0157 nan 0.0500 0.0001
## 40 0.0082 nan 0.0500 -0.0002
## 60 0.0051 nan 0.0500 0.0001
## 80 0.0035 nan 0.0500 -0.0000
## 100 0.0024 nan 0.0500 -0.0000
## 120 0.0016 nan 0.0500 0.0000
## 140 0.0012 nan 0.0500 -0.0000
## 160 0.0009 nan 0.0500 -0.0000
## 180 0.0007 nan 0.0500 -0.0000
## 200 0.0005 nan 0.0500 0.0000
##
## - Fold04: shrinkage=0.05, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold04: shrinkage=0.10, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0393 nan 0.1000 0.0059
## 2 0.0349 nan 0.1000 0.0043
## 3 0.0321 nan 0.1000 0.0025
## 4 0.0293 nan 0.1000 0.0022
## 5 0.0259 nan 0.1000 0.0010
## 6 0.0220 nan 0.1000 0.0034
## 7 0.0211 nan 0.1000 -0.0018
## 8 0.0195 nan 0.1000 0.0010
## 9 0.0180 nan 0.1000 0.0018
## 10 0.0156 nan 0.1000 0.0017
## 20 0.0075 nan 0.1000 0.0001
## 40 0.0018 nan 0.1000 0.0000
## 60 0.0007 nan 0.1000 0.0000
## 80 0.0003 nan 0.1000 -0.0000
## 100 0.0001 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold04: shrinkage=0.10, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold04: shrinkage=0.10, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0403 nan 0.1000 0.0025
## 2 0.0344 nan 0.1000 0.0053
## 3 0.0301 nan 0.1000 0.0039
## 4 0.0267 nan 0.1000 0.0031
## 5 0.0240 nan 0.1000 0.0029
## 6 0.0226 nan 0.1000 0.0007
## 7 0.0193 nan 0.1000 0.0018
## 8 0.0170 nan 0.1000 0.0013
## 9 0.0161 nan 0.1000 -0.0004
## 10 0.0141 nan 0.1000 0.0010
## 20 0.0064 nan 0.1000 -0.0004
## 40 0.0019 nan 0.1000 -0.0000
## 60 0.0009 nan 0.1000 -0.0001
## 80 0.0004 nan 0.1000 0.0000
## 100 0.0002 nan 0.1000 -0.0000
## 120 0.0001 nan 0.1000 0.0000
## 140 0.0001 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 0.0000
##
## - Fold04: shrinkage=0.10, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold04: shrinkage=0.10, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0366 nan 0.1000 0.0045
## 2 0.0318 nan 0.1000 0.0042
## 3 0.0279 nan 0.1000 0.0034
## 4 0.0255 nan 0.1000 0.0009
## 5 0.0232 nan 0.1000 0.0017
## 6 0.0213 nan 0.1000 -0.0006
## 7 0.0196 nan 0.1000 0.0012
## 8 0.0183 nan 0.1000 0.0010
## 9 0.0175 nan 0.1000 -0.0001
## 10 0.0163 nan 0.1000 0.0014
## 20 0.0090 nan 0.1000 -0.0007
## 40 0.0045 nan 0.1000 -0.0001
## 60 0.0024 nan 0.1000 -0.0001
## 80 0.0011 nan 0.1000 -0.0000
## 100 0.0009 nan 0.1000 0.0000
## 120 0.0006 nan 0.1000 -0.0000
## 140 0.0004 nan 0.1000 -0.0000
## 160 0.0003 nan 0.1000 -0.0000
## 180 0.0002 nan 0.1000 -0.0000
## 200 0.0001 nan 0.1000 -0.0000
##
## - Fold04: shrinkage=0.10, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold04: shrinkage=0.10, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0378 nan 0.1000 0.0046
## 2 0.0344 nan 0.1000 -0.0002
## 3 0.0287 nan 0.1000 0.0048
## 4 0.0249 nan 0.1000 0.0026
## 5 0.0216 nan 0.1000 0.0022
## 6 0.0191 nan 0.1000 0.0022
## 7 0.0172 nan 0.1000 0.0013
## 8 0.0150 nan 0.1000 0.0025
## 9 0.0133 nan 0.1000 0.0008
## 10 0.0117 nan 0.1000 0.0012
## 20 0.0036 nan 0.1000 0.0000
## 40 0.0006 nan 0.1000 -0.0000
## 60 0.0001 nan 0.1000 -0.0000
## 80 0.0000 nan 0.1000 0.0000
## 100 0.0000 nan 0.1000 0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 0.0000
##
## - Fold04: shrinkage=0.10, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold04: shrinkage=0.10, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0401 nan 0.1000 0.0040
## 2 0.0343 nan 0.1000 0.0051
## 3 0.0296 nan 0.1000 0.0037
## 4 0.0255 nan 0.1000 0.0037
## 5 0.0240 nan 0.1000 -0.0003
## 6 0.0210 nan 0.1000 0.0029
## 7 0.0187 nan 0.1000 0.0027
## 8 0.0166 nan 0.1000 0.0010
## 9 0.0141 nan 0.1000 0.0011
## 10 0.0124 nan 0.1000 0.0018
## 20 0.0053 nan 0.1000 0.0001
## 40 0.0012 nan 0.1000 -0.0001
## 60 0.0002 nan 0.1000 -0.0000
## 80 0.0001 nan 0.1000 -0.0000
## 100 0.0000 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 0.0000
##
## - Fold04: shrinkage=0.10, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold04: shrinkage=0.10, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0379 nan 0.1000 0.0059
## 2 0.0328 nan 0.1000 0.0044
## 3 0.0317 nan 0.1000 -0.0011
## 4 0.0288 nan 0.1000 0.0017
## 5 0.0261 nan 0.1000 0.0033
## 6 0.0235 nan 0.1000 0.0029
## 7 0.0222 nan 0.1000 0.0000
## 8 0.0194 nan 0.1000 0.0017
## 9 0.0175 nan 0.1000 0.0005
## 10 0.0151 nan 0.1000 0.0012
## 20 0.0084 nan 0.1000 0.0002
## 40 0.0032 nan 0.1000 0.0000
## 60 0.0015 nan 0.1000 0.0000
## 80 0.0010 nan 0.1000 -0.0000
## 100 0.0005 nan 0.1000 -0.0000
## 120 0.0003 nan 0.1000 -0.0000
## 140 0.0002 nan 0.1000 -0.0000
## 160 0.0001 nan 0.1000 -0.0000
## 180 0.0001 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold04: shrinkage=0.10, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold04: shrinkage=0.10, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0389 nan 0.1000 0.0030
## 2 0.0347 nan 0.1000 0.0020
## 3 0.0305 nan 0.1000 0.0041
## 4 0.0247 nan 0.1000 0.0055
## 5 0.0217 nan 0.1000 0.0028
## 6 0.0192 nan 0.1000 0.0018
## 7 0.0164 nan 0.1000 0.0033
## 8 0.0151 nan 0.1000 0.0011
## 9 0.0135 nan 0.1000 0.0014
## 10 0.0122 nan 0.1000 0.0008
## 20 0.0034 nan 0.1000 0.0006
## 40 0.0008 nan 0.1000 0.0000
## 60 0.0002 nan 0.1000 -0.0000
## 80 0.0000 nan 0.1000 -0.0000
## 100 0.0000 nan 0.1000 0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold04: shrinkage=0.10, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold04: shrinkage=0.10, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0425 nan 0.1000 -0.0013
## 2 0.0360 nan 0.1000 0.0049
## 3 0.0316 nan 0.1000 0.0048
## 4 0.0275 nan 0.1000 0.0039
## 5 0.0238 nan 0.1000 0.0034
## 6 0.0196 nan 0.1000 0.0021
## 7 0.0172 nan 0.1000 0.0015
## 8 0.0151 nan 0.1000 0.0018
## 9 0.0134 nan 0.1000 0.0015
## 10 0.0115 nan 0.1000 0.0009
## 20 0.0033 nan 0.1000 -0.0000
## 40 0.0009 nan 0.1000 0.0000
## 60 0.0003 nan 0.1000 -0.0000
## 80 0.0001 nan 0.1000 0.0000
## 100 0.0001 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold04: shrinkage=0.10, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold04: shrinkage=0.10, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0379 nan 0.1000 0.0059
## 2 0.0337 nan 0.1000 0.0037
## 3 0.0292 nan 0.1000 0.0029
## 4 0.0268 nan 0.1000 0.0005
## 5 0.0252 nan 0.1000 0.0014
## 6 0.0221 nan 0.1000 0.0031
## 7 0.0199 nan 0.1000 0.0023
## 8 0.0174 nan 0.1000 0.0020
## 9 0.0161 nan 0.1000 0.0007
## 10 0.0144 nan 0.1000 0.0016
## 20 0.0084 nan 0.1000 -0.0005
## 40 0.0028 nan 0.1000 0.0001
## 60 0.0013 nan 0.1000 -0.0000
## 80 0.0007 nan 0.1000 0.0000
## 100 0.0004 nan 0.1000 -0.0000
## 120 0.0002 nan 0.1000 -0.0000
## 140 0.0001 nan 0.1000 -0.0000
## 160 0.0001 nan 0.1000 0.0000
## 180 0.0001 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 0.0000
##
## - Fold04: shrinkage=0.10, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold05: shrinkage=0.01, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0433 nan 0.0100 0.0001
## 2 0.0427 nan 0.0100 0.0004
## 3 0.0422 nan 0.0100 0.0003
## 4 0.0418 nan 0.0100 0.0002
## 5 0.0412 nan 0.0100 0.0005
## 6 0.0406 nan 0.0100 0.0004
## 7 0.0401 nan 0.0100 0.0005
## 8 0.0395 nan 0.0100 0.0005
## 9 0.0390 nan 0.0100 0.0005
## 10 0.0385 nan 0.0100 0.0003
## 20 0.0343 nan 0.0100 0.0004
## 40 0.0277 nan 0.0100 0.0001
## 60 0.0221 nan 0.0100 0.0003
## 80 0.0182 nan 0.0100 0.0001
## 100 0.0147 nan 0.0100 0.0000
## 120 0.0121 nan 0.0100 0.0001
## 140 0.0099 nan 0.0100 0.0000
## 160 0.0083 nan 0.0100 0.0001
## 180 0.0069 nan 0.0100 0.0000
## 200 0.0060 nan 0.0100 0.0000
##
## - Fold05: shrinkage=0.01, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold05: shrinkage=0.01, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0429 nan 0.0100 0.0006
## 2 0.0425 nan 0.0100 0.0001
## 3 0.0419 nan 0.0100 0.0005
## 4 0.0415 nan 0.0100 0.0004
## 5 0.0409 nan 0.0100 0.0006
## 6 0.0404 nan 0.0100 0.0004
## 7 0.0399 nan 0.0100 0.0004
## 8 0.0394 nan 0.0100 0.0005
## 9 0.0388 nan 0.0100 0.0003
## 10 0.0385 nan 0.0100 0.0004
## 20 0.0339 nan 0.0100 0.0003
## 40 0.0275 nan 0.0100 0.0002
## 60 0.0220 nan 0.0100 0.0001
## 80 0.0179 nan 0.0100 0.0002
## 100 0.0147 nan 0.0100 0.0002
## 120 0.0122 nan 0.0100 0.0001
## 140 0.0102 nan 0.0100 0.0001
## 160 0.0085 nan 0.0100 -0.0000
## 180 0.0074 nan 0.0100 0.0001
## 200 0.0063 nan 0.0100 0.0000
##
## - Fold05: shrinkage=0.01, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold05: shrinkage=0.01, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0429 nan 0.0100 0.0006
## 2 0.0424 nan 0.0100 0.0002
## 3 0.0420 nan 0.0100 0.0004
## 4 0.0415 nan 0.0100 0.0005
## 5 0.0411 nan 0.0100 0.0003
## 6 0.0408 nan 0.0100 0.0002
## 7 0.0405 nan 0.0100 0.0001
## 8 0.0401 nan 0.0100 0.0003
## 9 0.0395 nan 0.0100 0.0005
## 10 0.0391 nan 0.0100 0.0005
## 20 0.0347 nan 0.0100 0.0001
## 40 0.0282 nan 0.0100 0.0003
## 60 0.0232 nan 0.0100 0.0002
## 80 0.0196 nan 0.0100 0.0000
## 100 0.0165 nan 0.0100 0.0001
## 120 0.0141 nan 0.0100 -0.0000
## 140 0.0123 nan 0.0100 -0.0000
## 160 0.0108 nan 0.0100 0.0000
## 180 0.0096 nan 0.0100 0.0001
## 200 0.0084 nan 0.0100 -0.0000
##
## - Fold05: shrinkage=0.01, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold05: shrinkage=0.01, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0430 nan 0.0100 0.0004
## 2 0.0422 nan 0.0100 0.0006
## 3 0.0414 nan 0.0100 0.0007
## 4 0.0411 nan 0.0100 0.0000
## 5 0.0403 nan 0.0100 0.0005
## 6 0.0399 nan 0.0100 0.0002
## 7 0.0393 nan 0.0100 0.0004
## 8 0.0387 nan 0.0100 0.0004
## 9 0.0381 nan 0.0100 0.0006
## 10 0.0374 nan 0.0100 0.0004
## 20 0.0329 nan 0.0100 0.0003
## 40 0.0253 nan 0.0100 0.0001
## 60 0.0191 nan 0.0100 0.0002
## 80 0.0149 nan 0.0100 0.0000
## 100 0.0119 nan 0.0100 0.0001
## 120 0.0092 nan 0.0100 0.0000
## 140 0.0074 nan 0.0100 -0.0000
## 160 0.0059 nan 0.0100 0.0000
## 180 0.0046 nan 0.0100 0.0000
## 200 0.0037 nan 0.0100 0.0000
##
## - Fold05: shrinkage=0.01, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold05: shrinkage=0.01, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0432 nan 0.0100 0.0003
## 2 0.0424 nan 0.0100 0.0007
## 3 0.0417 nan 0.0100 0.0007
## 4 0.0411 nan 0.0100 0.0006
## 5 0.0406 nan 0.0100 0.0005
## 6 0.0402 nan 0.0100 0.0005
## 7 0.0397 nan 0.0100 0.0004
## 8 0.0395 nan 0.0100 -0.0000
## 9 0.0390 nan 0.0100 0.0001
## 10 0.0386 nan 0.0100 0.0002
## 20 0.0333 nan 0.0100 0.0004
## 40 0.0261 nan 0.0100 0.0003
## 60 0.0198 nan 0.0100 0.0003
## 80 0.0155 nan 0.0100 0.0001
## 100 0.0121 nan 0.0100 0.0001
## 120 0.0097 nan 0.0100 0.0001
## 140 0.0080 nan 0.0100 0.0000
## 160 0.0063 nan 0.0100 0.0000
## 180 0.0052 nan 0.0100 0.0000
## 200 0.0044 nan 0.0100 0.0000
##
## - Fold05: shrinkage=0.01, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold05: shrinkage=0.01, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0430 nan 0.0100 0.0005
## 2 0.0426 nan 0.0100 0.0003
## 3 0.0421 nan 0.0100 0.0005
## 4 0.0416 nan 0.0100 0.0003
## 5 0.0411 nan 0.0100 0.0006
## 6 0.0406 nan 0.0100 0.0002
## 7 0.0402 nan 0.0100 0.0003
## 8 0.0398 nan 0.0100 0.0005
## 9 0.0393 nan 0.0100 0.0005
## 10 0.0388 nan 0.0100 0.0005
## 20 0.0352 nan 0.0100 0.0003
## 40 0.0287 nan 0.0100 0.0000
## 60 0.0237 nan 0.0100 0.0000
## 80 0.0202 nan 0.0100 -0.0001
## 100 0.0170 nan 0.0100 0.0001
## 120 0.0145 nan 0.0100 -0.0001
## 140 0.0127 nan 0.0100 0.0000
## 160 0.0111 nan 0.0100 -0.0000
## 180 0.0099 nan 0.0100 -0.0000
## 200 0.0089 nan 0.0100 -0.0000
##
## - Fold05: shrinkage=0.01, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold05: shrinkage=0.01, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0428 nan 0.0100 0.0005
## 2 0.0422 nan 0.0100 0.0005
## 3 0.0417 nan 0.0100 0.0006
## 4 0.0411 nan 0.0100 0.0006
## 5 0.0404 nan 0.0100 0.0003
## 6 0.0398 nan 0.0100 0.0004
## 7 0.0390 nan 0.0100 0.0007
## 8 0.0383 nan 0.0100 0.0009
## 9 0.0377 nan 0.0100 0.0004
## 10 0.0370 nan 0.0100 0.0004
## 20 0.0315 nan 0.0100 0.0002
## 40 0.0239 nan 0.0100 0.0002
## 60 0.0178 nan 0.0100 0.0002
## 80 0.0134 nan 0.0100 0.0002
## 100 0.0103 nan 0.0100 0.0001
## 120 0.0081 nan 0.0100 0.0000
## 140 0.0064 nan 0.0100 0.0001
## 160 0.0050 nan 0.0100 0.0001
## 180 0.0040 nan 0.0100 0.0000
## 200 0.0032 nan 0.0100 0.0000
##
## - Fold05: shrinkage=0.01, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold05: shrinkage=0.01, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0430 nan 0.0100 0.0007
## 2 0.0425 nan 0.0100 0.0004
## 3 0.0419 nan 0.0100 0.0005
## 4 0.0415 nan 0.0100 0.0002
## 5 0.0410 nan 0.0100 0.0005
## 6 0.0404 nan 0.0100 0.0006
## 7 0.0397 nan 0.0100 0.0006
## 8 0.0391 nan 0.0100 0.0005
## 9 0.0386 nan 0.0100 0.0003
## 10 0.0381 nan 0.0100 0.0003
## 20 0.0332 nan 0.0100 0.0004
## 40 0.0253 nan 0.0100 0.0001
## 60 0.0197 nan 0.0100 0.0002
## 80 0.0155 nan 0.0100 0.0000
## 100 0.0118 nan 0.0100 0.0002
## 120 0.0092 nan 0.0100 0.0001
## 140 0.0073 nan 0.0100 0.0000
## 160 0.0059 nan 0.0100 0.0000
## 180 0.0049 nan 0.0100 0.0000
## 200 0.0041 nan 0.0100 0.0000
##
## - Fold05: shrinkage=0.01, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold05: shrinkage=0.01, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0430 nan 0.0100 0.0004
## 2 0.0425 nan 0.0100 0.0006
## 3 0.0421 nan 0.0100 0.0002
## 4 0.0414 nan 0.0100 0.0006
## 5 0.0408 nan 0.0100 0.0005
## 6 0.0404 nan 0.0100 0.0004
## 7 0.0401 nan 0.0100 0.0002
## 8 0.0395 nan 0.0100 0.0004
## 9 0.0392 nan 0.0100 0.0001
## 10 0.0390 nan 0.0100 0.0000
## 20 0.0342 nan 0.0100 -0.0000
## 40 0.0277 nan 0.0100 0.0002
## 60 0.0226 nan 0.0100 0.0002
## 80 0.0187 nan 0.0100 0.0000
## 100 0.0158 nan 0.0100 0.0001
## 120 0.0133 nan 0.0100 0.0000
## 140 0.0115 nan 0.0100 0.0001
## 160 0.0104 nan 0.0100 0.0001
## 180 0.0090 nan 0.0100 -0.0000
## 200 0.0080 nan 0.0100 0.0000
##
## - Fold05: shrinkage=0.01, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold05: shrinkage=0.05, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0408 nan 0.0500 0.0025
## 2 0.0387 nan 0.0500 0.0022
## 3 0.0367 nan 0.0500 0.0023
## 4 0.0339 nan 0.0500 0.0021
## 5 0.0324 nan 0.0500 0.0011
## 6 0.0311 nan 0.0500 0.0007
## 7 0.0298 nan 0.0500 0.0006
## 8 0.0282 nan 0.0500 0.0015
## 9 0.0267 nan 0.0500 0.0015
## 10 0.0252 nan 0.0500 0.0011
## 20 0.0156 nan 0.0500 -0.0000
## 40 0.0067 nan 0.0500 0.0003
## 60 0.0037 nan 0.0500 0.0001
## 80 0.0020 nan 0.0500 0.0000
## 100 0.0010 nan 0.0500 -0.0000
## 120 0.0007 nan 0.0500 -0.0000
## 140 0.0004 nan 0.0500 -0.0000
## 160 0.0002 nan 0.0500 0.0000
## 180 0.0001 nan 0.0500 0.0000
## 200 0.0001 nan 0.0500 0.0000
##
## - Fold05: shrinkage=0.05, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold05: shrinkage=0.05, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0405 nan 0.0500 0.0028
## 2 0.0385 nan 0.0500 0.0025
## 3 0.0355 nan 0.0500 0.0019
## 4 0.0338 nan 0.0500 0.0016
## 5 0.0312 nan 0.0500 0.0014
## 6 0.0294 nan 0.0500 0.0016
## 7 0.0276 nan 0.0500 0.0013
## 8 0.0266 nan 0.0500 0.0004
## 9 0.0253 nan 0.0500 0.0006
## 10 0.0240 nan 0.0500 0.0011
## 20 0.0149 nan 0.0500 0.0003
## 40 0.0064 nan 0.0500 0.0001
## 60 0.0032 nan 0.0500 0.0000
## 80 0.0018 nan 0.0500 -0.0000
## 100 0.0012 nan 0.0500 -0.0001
## 120 0.0007 nan 0.0500 0.0000
## 140 0.0004 nan 0.0500 -0.0000
## 160 0.0003 nan 0.0500 -0.0000
## 180 0.0002 nan 0.0500 -0.0000
## 200 0.0001 nan 0.0500 -0.0000
##
## - Fold05: shrinkage=0.05, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold05: shrinkage=0.05, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0410 nan 0.0500 0.0019
## 2 0.0390 nan 0.0500 0.0018
## 3 0.0363 nan 0.0500 0.0022
## 4 0.0344 nan 0.0500 0.0022
## 5 0.0320 nan 0.0500 0.0014
## 6 0.0309 nan 0.0500 0.0005
## 7 0.0290 nan 0.0500 0.0017
## 8 0.0275 nan 0.0500 0.0013
## 9 0.0260 nan 0.0500 0.0013
## 10 0.0243 nan 0.0500 0.0009
## 20 0.0160 nan 0.0500 0.0004
## 40 0.0103 nan 0.0500 0.0002
## 60 0.0059 nan 0.0500 0.0002
## 80 0.0034 nan 0.0500 -0.0000
## 100 0.0022 nan 0.0500 -0.0000
## 120 0.0017 nan 0.0500 -0.0001
## 140 0.0012 nan 0.0500 -0.0000
## 160 0.0009 nan 0.0500 0.0000
## 180 0.0007 nan 0.0500 -0.0000
## 200 0.0006 nan 0.0500 -0.0000
##
## - Fold05: shrinkage=0.05, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold05: shrinkage=0.05, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0403 nan 0.0500 0.0025
## 2 0.0384 nan 0.0500 0.0007
## 3 0.0361 nan 0.0500 0.0019
## 4 0.0352 nan 0.0500 -0.0006
## 5 0.0333 nan 0.0500 0.0003
## 6 0.0308 nan 0.0500 0.0008
## 7 0.0284 nan 0.0500 0.0016
## 8 0.0264 nan 0.0500 0.0016
## 9 0.0257 nan 0.0500 0.0002
## 10 0.0243 nan 0.0500 0.0015
## 20 0.0142 nan 0.0500 0.0008
## 40 0.0046 nan 0.0500 0.0001
## 60 0.0018 nan 0.0500 0.0000
## 80 0.0007 nan 0.0500 -0.0000
## 100 0.0003 nan 0.0500 0.0000
## 120 0.0002 nan 0.0500 -0.0000
## 140 0.0001 nan 0.0500 0.0000
## 160 0.0000 nan 0.0500 -0.0000
## 180 0.0000 nan 0.0500 -0.0000
## 200 0.0000 nan 0.0500 0.0000
##
## - Fold05: shrinkage=0.05, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold05: shrinkage=0.05, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0405 nan 0.0500 0.0031
## 2 0.0372 nan 0.0500 0.0023
## 3 0.0339 nan 0.0500 0.0026
## 4 0.0324 nan 0.0500 0.0011
## 5 0.0299 nan 0.0500 0.0016
## 6 0.0280 nan 0.0500 0.0018
## 7 0.0270 nan 0.0500 0.0004
## 8 0.0261 nan 0.0500 0.0006
## 9 0.0245 nan 0.0500 0.0009
## 10 0.0236 nan 0.0500 0.0008
## 20 0.0136 nan 0.0500 0.0003
## 40 0.0047 nan 0.0500 0.0001
## 60 0.0020 nan 0.0500 -0.0000
## 80 0.0011 nan 0.0500 -0.0000
## 100 0.0006 nan 0.0500 -0.0000
## 120 0.0003 nan 0.0500 0.0000
## 140 0.0002 nan 0.0500 -0.0000
## 160 0.0001 nan 0.0500 -0.0000
## 180 0.0001 nan 0.0500 -0.0000
## 200 0.0001 nan 0.0500 -0.0000
##
## - Fold05: shrinkage=0.05, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold05: shrinkage=0.05, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0423 nan 0.0500 0.0003
## 2 0.0394 nan 0.0500 0.0025
## 3 0.0373 nan 0.0500 0.0018
## 4 0.0357 nan 0.0500 0.0020
## 5 0.0335 nan 0.0500 0.0014
## 6 0.0315 nan 0.0500 0.0011
## 7 0.0302 nan 0.0500 0.0004
## 8 0.0288 nan 0.0500 0.0006
## 9 0.0270 nan 0.0500 0.0017
## 10 0.0267 nan 0.0500 -0.0005
## 20 0.0176 nan 0.0500 0.0005
## 40 0.0088 nan 0.0500 -0.0003
## 60 0.0053 nan 0.0500 -0.0001
## 80 0.0033 nan 0.0500 0.0001
## 100 0.0023 nan 0.0500 0.0000
## 120 0.0017 nan 0.0500 -0.0000
## 140 0.0012 nan 0.0500 -0.0000
## 160 0.0008 nan 0.0500 -0.0000
## 180 0.0006 nan 0.0500 0.0000
## 200 0.0004 nan 0.0500 -0.0000
##
## - Fold05: shrinkage=0.05, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold05: shrinkage=0.05, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0404 nan 0.0500 0.0006
## 2 0.0369 nan 0.0500 0.0030
## 3 0.0350 nan 0.0500 0.0004
## 4 0.0328 nan 0.0500 0.0018
## 5 0.0305 nan 0.0500 0.0027
## 6 0.0285 nan 0.0500 0.0008
## 7 0.0260 nan 0.0500 0.0010
## 8 0.0241 nan 0.0500 0.0013
## 9 0.0221 nan 0.0500 0.0015
## 10 0.0205 nan 0.0500 0.0014
## 20 0.0109 nan 0.0500 0.0001
## 40 0.0036 nan 0.0500 0.0000
## 60 0.0012 nan 0.0500 0.0001
## 80 0.0004 nan 0.0500 0.0000
## 100 0.0002 nan 0.0500 -0.0000
## 120 0.0001 nan 0.0500 0.0000
## 140 0.0000 nan 0.0500 -0.0000
## 160 0.0000 nan 0.0500 -0.0000
## 180 0.0000 nan 0.0500 -0.0000
## 200 0.0000 nan 0.0500 -0.0000
##
## - Fold05: shrinkage=0.05, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold05: shrinkage=0.05, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0407 nan 0.0500 0.0029
## 2 0.0387 nan 0.0500 0.0015
## 3 0.0355 nan 0.0500 0.0025
## 4 0.0344 nan 0.0500 0.0008
## 5 0.0319 nan 0.0500 0.0024
## 6 0.0301 nan 0.0500 0.0012
## 7 0.0280 nan 0.0500 0.0010
## 8 0.0259 nan 0.0500 0.0002
## 9 0.0249 nan 0.0500 0.0007
## 10 0.0231 nan 0.0500 0.0007
## 20 0.0127 nan 0.0500 0.0001
## 40 0.0039 nan 0.0500 -0.0000
## 60 0.0017 nan 0.0500 -0.0000
## 80 0.0007 nan 0.0500 0.0000
## 100 0.0004 nan 0.0500 0.0000
## 120 0.0002 nan 0.0500 0.0000
## 140 0.0001 nan 0.0500 -0.0000
## 160 0.0001 nan 0.0500 -0.0000
## 180 0.0000 nan 0.0500 0.0000
## 200 0.0000 nan 0.0500 -0.0000
##
## - Fold05: shrinkage=0.05, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold05: shrinkage=0.05, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0409 nan 0.0500 0.0019
## 2 0.0390 nan 0.0500 0.0016
## 3 0.0386 nan 0.0500 -0.0012
## 4 0.0359 nan 0.0500 0.0025
## 5 0.0338 nan 0.0500 0.0018
## 6 0.0324 nan 0.0500 0.0012
## 7 0.0311 nan 0.0500 0.0006
## 8 0.0298 nan 0.0500 0.0016
## 9 0.0281 nan 0.0500 0.0011
## 10 0.0273 nan 0.0500 -0.0000
## 20 0.0188 nan 0.0500 0.0003
## 40 0.0102 nan 0.0500 -0.0000
## 60 0.0061 nan 0.0500 -0.0001
## 80 0.0038 nan 0.0500 -0.0000
## 100 0.0027 nan 0.0500 -0.0000
## 120 0.0019 nan 0.0500 -0.0001
## 140 0.0014 nan 0.0500 -0.0000
## 160 0.0010 nan 0.0500 -0.0000
## 180 0.0007 nan 0.0500 -0.0000
## 200 0.0006 nan 0.0500 -0.0000
##
## - Fold05: shrinkage=0.05, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold05: shrinkage=0.10, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0376 nan 0.1000 0.0056
## 2 0.0334 nan 0.1000 0.0021
## 3 0.0292 nan 0.1000 0.0040
## 4 0.0255 nan 0.1000 0.0032
## 5 0.0241 nan 0.1000 0.0005
## 6 0.0223 nan 0.1000 0.0018
## 7 0.0202 nan 0.1000 0.0021
## 8 0.0186 nan 0.1000 0.0002
## 9 0.0165 nan 0.1000 0.0018
## 10 0.0153 nan 0.1000 0.0009
## 20 0.0060 nan 0.1000 0.0004
## 40 0.0016 nan 0.1000 -0.0001
## 60 0.0006 nan 0.1000 0.0000
## 80 0.0002 nan 0.1000 -0.0000
## 100 0.0001 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold05: shrinkage=0.10, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold05: shrinkage=0.10, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0384 nan 0.1000 0.0040
## 2 0.0343 nan 0.1000 0.0042
## 3 0.0309 nan 0.1000 0.0005
## 4 0.0279 nan 0.1000 0.0017
## 5 0.0250 nan 0.1000 0.0019
## 6 0.0229 nan 0.1000 -0.0004
## 7 0.0204 nan 0.1000 0.0011
## 8 0.0192 nan 0.1000 0.0002
## 9 0.0180 nan 0.1000 0.0012
## 10 0.0156 nan 0.1000 0.0012
## 20 0.0070 nan 0.1000 0.0001
## 40 0.0019 nan 0.1000 0.0000
## 60 0.0007 nan 0.1000 -0.0000
## 80 0.0003 nan 0.1000 -0.0000
## 100 0.0001 nan 0.1000 0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 0.0000
##
## - Fold05: shrinkage=0.10, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold05: shrinkage=0.10, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0370 nan 0.1000 0.0054
## 2 0.0343 nan 0.1000 0.0027
## 3 0.0299 nan 0.1000 0.0022
## 4 0.0265 nan 0.1000 0.0030
## 5 0.0247 nan 0.1000 0.0008
## 6 0.0216 nan 0.1000 0.0029
## 7 0.0199 nan 0.1000 0.0008
## 8 0.0177 nan 0.1000 0.0021
## 9 0.0160 nan 0.1000 0.0017
## 10 0.0148 nan 0.1000 0.0007
## 20 0.0085 nan 0.1000 0.0001
## 40 0.0036 nan 0.1000 -0.0003
## 60 0.0012 nan 0.1000 -0.0001
## 80 0.0007 nan 0.1000 0.0000
## 100 0.0004 nan 0.1000 -0.0000
## 120 0.0003 nan 0.1000 -0.0000
## 140 0.0002 nan 0.1000 -0.0000
## 160 0.0001 nan 0.1000 0.0000
## 180 0.0001 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold05: shrinkage=0.10, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold05: shrinkage=0.10, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0383 nan 0.1000 0.0045
## 2 0.0332 nan 0.1000 0.0036
## 3 0.0297 nan 0.1000 0.0017
## 4 0.0259 nan 0.1000 0.0009
## 5 0.0228 nan 0.1000 0.0024
## 6 0.0198 nan 0.1000 0.0018
## 7 0.0180 nan 0.1000 0.0012
## 8 0.0166 nan 0.1000 0.0008
## 9 0.0140 nan 0.1000 0.0012
## 10 0.0126 nan 0.1000 0.0014
## 20 0.0039 nan 0.1000 0.0003
## 40 0.0007 nan 0.1000 0.0000
## 60 0.0002 nan 0.1000 -0.0000
## 80 0.0000 nan 0.1000 -0.0000
## 100 0.0000 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold05: shrinkage=0.10, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold05: shrinkage=0.10, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0381 nan 0.1000 0.0003
## 2 0.0322 nan 0.1000 0.0050
## 3 0.0284 nan 0.1000 0.0043
## 4 0.0251 nan 0.1000 0.0032
## 5 0.0225 nan 0.1000 0.0019
## 6 0.0198 nan 0.1000 0.0029
## 7 0.0172 nan 0.1000 0.0017
## 8 0.0162 nan 0.1000 -0.0002
## 9 0.0149 nan 0.1000 -0.0012
## 10 0.0140 nan 0.1000 0.0005
## 20 0.0048 nan 0.1000 -0.0000
## 40 0.0011 nan 0.1000 -0.0001
## 60 0.0004 nan 0.1000 -0.0000
## 80 0.0001 nan 0.1000 -0.0000
## 100 0.0001 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold05: shrinkage=0.10, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold05: shrinkage=0.10, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0384 nan 0.1000 0.0054
## 2 0.0341 nan 0.1000 0.0035
## 3 0.0307 nan 0.1000 0.0037
## 4 0.0278 nan 0.1000 0.0000
## 5 0.0253 nan 0.1000 0.0002
## 6 0.0228 nan 0.1000 0.0026
## 7 0.0204 nan 0.1000 0.0020
## 8 0.0186 nan 0.1000 0.0007
## 9 0.0178 nan 0.1000 -0.0004
## 10 0.0159 nan 0.1000 0.0007
## 20 0.0079 nan 0.1000 0.0001
## 40 0.0027 nan 0.1000 -0.0001
## 60 0.0014 nan 0.1000 -0.0000
## 80 0.0009 nan 0.1000 -0.0000
## 100 0.0005 nan 0.1000 -0.0000
## 120 0.0004 nan 0.1000 -0.0000
## 140 0.0002 nan 0.1000 0.0000
## 160 0.0001 nan 0.1000 -0.0000
## 180 0.0001 nan 0.1000 -0.0000
## 200 0.0001 nan 0.1000 -0.0000
##
## - Fold05: shrinkage=0.10, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold05: shrinkage=0.10, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0376 nan 0.1000 0.0048
## 2 0.0333 nan 0.1000 0.0027
## 3 0.0281 nan 0.1000 0.0024
## 4 0.0242 nan 0.1000 0.0024
## 5 0.0210 nan 0.1000 0.0032
## 6 0.0172 nan 0.1000 0.0022
## 7 0.0139 nan 0.1000 0.0022
## 8 0.0125 nan 0.1000 0.0008
## 9 0.0111 nan 0.1000 0.0014
## 10 0.0096 nan 0.1000 0.0007
## 20 0.0025 nan 0.1000 0.0002
## 40 0.0005 nan 0.1000 -0.0000
## 60 0.0001 nan 0.1000 0.0000
## 80 0.0000 nan 0.1000 -0.0000
## 100 0.0000 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold05: shrinkage=0.10, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold05: shrinkage=0.10, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0368 nan 0.1000 0.0043
## 2 0.0314 nan 0.1000 0.0050
## 3 0.0283 nan 0.1000 -0.0017
## 4 0.0248 nan 0.1000 0.0030
## 5 0.0230 nan 0.1000 0.0007
## 6 0.0200 nan 0.1000 0.0027
## 7 0.0191 nan 0.1000 -0.0009
## 8 0.0163 nan 0.1000 0.0009
## 9 0.0149 nan 0.1000 0.0015
## 10 0.0134 nan 0.1000 0.0010
## 20 0.0053 nan 0.1000 -0.0003
## 40 0.0014 nan 0.1000 0.0001
## 60 0.0005 nan 0.1000 -0.0001
## 80 0.0002 nan 0.1000 -0.0000
## 100 0.0001 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold05: shrinkage=0.10, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold05: shrinkage=0.10, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0415 nan 0.1000 -0.0008
## 2 0.0365 nan 0.1000 0.0054
## 3 0.0321 nan 0.1000 0.0046
## 4 0.0283 nan 0.1000 0.0036
## 5 0.0246 nan 0.1000 0.0025
## 6 0.0220 nan 0.1000 0.0025
## 7 0.0204 nan 0.1000 0.0002
## 8 0.0190 nan 0.1000 0.0007
## 9 0.0169 nan 0.1000 0.0014
## 10 0.0156 nan 0.1000 0.0009
## 20 0.0092 nan 0.1000 0.0001
## 40 0.0043 nan 0.1000 -0.0001
## 60 0.0020 nan 0.1000 -0.0000
## 80 0.0011 nan 0.1000 -0.0001
## 100 0.0007 nan 0.1000 0.0000
## 120 0.0004 nan 0.1000 -0.0000
## 140 0.0002 nan 0.1000 0.0000
## 160 0.0001 nan 0.1000 -0.0000
## 180 0.0001 nan 0.1000 0.0000
## 200 0.0001 nan 0.1000 0.0000
##
## - Fold05: shrinkage=0.10, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold06: shrinkage=0.01, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0426 nan 0.0100 0.0005
## 2 0.0424 nan 0.0100 -0.0000
## 3 0.0418 nan 0.0100 0.0003
## 4 0.0415 nan 0.0100 0.0003
## 5 0.0409 nan 0.0100 0.0003
## 6 0.0406 nan 0.0100 0.0001
## 7 0.0401 nan 0.0100 0.0005
## 8 0.0395 nan 0.0100 0.0006
## 9 0.0389 nan 0.0100 0.0006
## 10 0.0384 nan 0.0100 0.0005
## 20 0.0344 nan 0.0100 0.0004
## 40 0.0279 nan 0.0100 0.0004
## 60 0.0230 nan 0.0100 0.0002
## 80 0.0185 nan 0.0100 0.0002
## 100 0.0155 nan 0.0100 0.0000
## 120 0.0127 nan 0.0100 0.0000
## 140 0.0107 nan 0.0100 0.0001
## 160 0.0090 nan 0.0100 0.0001
## 180 0.0077 nan 0.0100 0.0000
## 200 0.0064 nan 0.0100 0.0001
##
## - Fold06: shrinkage=0.01, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold06: shrinkage=0.01, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0426 nan 0.0100 0.0002
## 2 0.0421 nan 0.0100 0.0002
## 3 0.0415 nan 0.0100 0.0006
## 4 0.0412 nan 0.0100 -0.0000
## 5 0.0407 nan 0.0100 0.0005
## 6 0.0400 nan 0.0100 0.0005
## 7 0.0395 nan 0.0100 0.0003
## 8 0.0391 nan 0.0100 0.0005
## 9 0.0385 nan 0.0100 0.0004
## 10 0.0381 nan 0.0100 0.0003
## 20 0.0336 nan 0.0100 0.0001
## 40 0.0272 nan 0.0100 0.0003
## 60 0.0225 nan 0.0100 0.0000
## 80 0.0186 nan 0.0100 0.0001
## 100 0.0152 nan 0.0100 0.0001
## 120 0.0129 nan 0.0100 0.0001
## 140 0.0110 nan 0.0100 -0.0000
## 160 0.0094 nan 0.0100 0.0000
## 180 0.0077 nan 0.0100 0.0000
## 200 0.0066 nan 0.0100 0.0000
##
## - Fold06: shrinkage=0.01, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold06: shrinkage=0.01, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0425 nan 0.0100 0.0006
## 2 0.0418 nan 0.0100 0.0005
## 3 0.0412 nan 0.0100 0.0005
## 4 0.0409 nan 0.0100 0.0000
## 5 0.0404 nan 0.0100 0.0005
## 6 0.0400 nan 0.0100 0.0000
## 7 0.0396 nan 0.0100 0.0002
## 8 0.0391 nan 0.0100 0.0003
## 9 0.0386 nan 0.0100 0.0005
## 10 0.0383 nan 0.0100 0.0001
## 20 0.0344 nan 0.0100 0.0004
## 40 0.0271 nan 0.0100 0.0002
## 60 0.0225 nan 0.0100 0.0001
## 80 0.0190 nan 0.0100 0.0002
## 100 0.0161 nan 0.0100 -0.0000
## 120 0.0140 nan 0.0100 0.0001
## 140 0.0125 nan 0.0100 -0.0000
## 160 0.0110 nan 0.0100 -0.0000
## 180 0.0095 nan 0.0100 0.0001
## 200 0.0085 nan 0.0100 -0.0000
##
## - Fold06: shrinkage=0.01, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold06: shrinkage=0.01, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0425 nan 0.0100 0.0005
## 2 0.0419 nan 0.0100 0.0006
## 3 0.0411 nan 0.0100 0.0007
## 4 0.0405 nan 0.0100 0.0004
## 5 0.0400 nan 0.0100 0.0003
## 6 0.0394 nan 0.0100 0.0004
## 7 0.0389 nan 0.0100 0.0004
## 8 0.0386 nan 0.0100 0.0002
## 9 0.0380 nan 0.0100 0.0007
## 10 0.0373 nan 0.0100 0.0005
## 20 0.0319 nan 0.0100 0.0003
## 40 0.0246 nan 0.0100 0.0002
## 60 0.0186 nan 0.0100 0.0001
## 80 0.0146 nan 0.0100 0.0001
## 100 0.0115 nan 0.0100 -0.0000
## 120 0.0090 nan 0.0100 0.0001
## 140 0.0072 nan 0.0100 0.0000
## 160 0.0058 nan 0.0100 0.0000
## 180 0.0047 nan 0.0100 0.0000
## 200 0.0038 nan 0.0100 0.0000
##
## - Fold06: shrinkage=0.01, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold06: shrinkage=0.01, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0428 nan 0.0100 -0.0003
## 2 0.0419 nan 0.0100 0.0006
## 3 0.0412 nan 0.0100 0.0007
## 4 0.0406 nan 0.0100 0.0005
## 5 0.0399 nan 0.0100 0.0007
## 6 0.0393 nan 0.0100 0.0004
## 7 0.0388 nan 0.0100 0.0003
## 8 0.0383 nan 0.0100 0.0003
## 9 0.0378 nan 0.0100 0.0002
## 10 0.0372 nan 0.0100 0.0005
## 20 0.0327 nan 0.0100 0.0003
## 40 0.0248 nan 0.0100 0.0003
## 60 0.0196 nan 0.0100 0.0002
## 80 0.0156 nan 0.0100 0.0002
## 100 0.0122 nan 0.0100 0.0001
## 120 0.0100 nan 0.0100 0.0001
## 140 0.0083 nan 0.0100 0.0001
## 160 0.0066 nan 0.0100 -0.0000
## 180 0.0054 nan 0.0100 0.0000
## 200 0.0046 nan 0.0100 0.0001
##
## - Fold06: shrinkage=0.01, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold06: shrinkage=0.01, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0424 nan 0.0100 0.0005
## 2 0.0421 nan 0.0100 0.0003
## 3 0.0416 nan 0.0100 0.0004
## 4 0.0411 nan 0.0100 0.0003
## 5 0.0407 nan 0.0100 0.0004
## 6 0.0401 nan 0.0100 0.0005
## 7 0.0396 nan 0.0100 0.0004
## 8 0.0395 nan 0.0100 -0.0001
## 9 0.0391 nan 0.0100 0.0002
## 10 0.0388 nan 0.0100 -0.0000
## 20 0.0348 nan 0.0100 0.0005
## 40 0.0279 nan 0.0100 0.0003
## 60 0.0228 nan 0.0100 0.0002
## 80 0.0188 nan 0.0100 0.0001
## 100 0.0159 nan 0.0100 -0.0001
## 120 0.0138 nan 0.0100 -0.0000
## 140 0.0121 nan 0.0100 0.0000
## 160 0.0108 nan 0.0100 -0.0000
## 180 0.0094 nan 0.0100 0.0000
## 200 0.0086 nan 0.0100 -0.0000
##
## - Fold06: shrinkage=0.01, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold06: shrinkage=0.01, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0423 nan 0.0100 0.0008
## 2 0.0418 nan 0.0100 0.0006
## 3 0.0411 nan 0.0100 0.0005
## 4 0.0404 nan 0.0100 0.0004
## 5 0.0401 nan 0.0100 -0.0001
## 6 0.0394 nan 0.0100 0.0007
## 7 0.0387 nan 0.0100 0.0007
## 8 0.0382 nan 0.0100 0.0005
## 9 0.0378 nan 0.0100 0.0001
## 10 0.0372 nan 0.0100 0.0005
## 20 0.0316 nan 0.0100 0.0003
## 40 0.0239 nan 0.0100 0.0003
## 60 0.0184 nan 0.0100 0.0002
## 80 0.0138 nan 0.0100 0.0002
## 100 0.0107 nan 0.0100 0.0001
## 120 0.0084 nan 0.0100 0.0000
## 140 0.0066 nan 0.0100 -0.0000
## 160 0.0053 nan 0.0100 0.0000
## 180 0.0043 nan 0.0100 0.0000
## 200 0.0034 nan 0.0100 0.0000
##
## - Fold06: shrinkage=0.01, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold06: shrinkage=0.01, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0424 nan 0.0100 0.0006
## 2 0.0417 nan 0.0100 0.0006
## 3 0.0411 nan 0.0100 0.0002
## 4 0.0406 nan 0.0100 0.0002
## 5 0.0401 nan 0.0100 0.0005
## 6 0.0395 nan 0.0100 0.0004
## 7 0.0389 nan 0.0100 0.0006
## 8 0.0384 nan 0.0100 0.0003
## 9 0.0377 nan 0.0100 0.0008
## 10 0.0371 nan 0.0100 0.0004
## 20 0.0325 nan 0.0100 0.0004
## 40 0.0243 nan 0.0100 0.0002
## 60 0.0185 nan 0.0100 0.0002
## 80 0.0146 nan 0.0100 0.0002
## 100 0.0118 nan 0.0100 0.0001
## 120 0.0093 nan 0.0100 0.0001
## 140 0.0076 nan 0.0100 0.0000
## 160 0.0065 nan 0.0100 0.0000
## 180 0.0053 nan 0.0100 -0.0000
## 200 0.0045 nan 0.0100 0.0000
##
## - Fold06: shrinkage=0.01, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold06: shrinkage=0.01, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0424 nan 0.0100 0.0006
## 2 0.0417 nan 0.0100 0.0006
## 3 0.0412 nan 0.0100 0.0006
## 4 0.0411 nan 0.0100 0.0000
## 5 0.0408 nan 0.0100 -0.0001
## 6 0.0403 nan 0.0100 0.0005
## 7 0.0398 nan 0.0100 0.0005
## 8 0.0392 nan 0.0100 0.0004
## 9 0.0387 nan 0.0100 0.0005
## 10 0.0383 nan 0.0100 0.0000
## 20 0.0342 nan 0.0100 0.0004
## 40 0.0275 nan 0.0100 0.0002
## 60 0.0224 nan 0.0100 0.0002
## 80 0.0187 nan 0.0100 0.0002
## 100 0.0156 nan 0.0100 0.0001
## 120 0.0132 nan 0.0100 0.0001
## 140 0.0117 nan 0.0100 0.0001
## 160 0.0102 nan 0.0100 0.0001
## 180 0.0089 nan 0.0100 -0.0000
## 200 0.0078 nan 0.0100 -0.0000
##
## - Fold06: shrinkage=0.01, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold06: shrinkage=0.05, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0413 nan 0.0500 0.0003
## 2 0.0387 nan 0.0500 0.0019
## 3 0.0358 nan 0.0500 0.0026
## 4 0.0336 nan 0.0500 0.0017
## 5 0.0318 nan 0.0500 0.0006
## 6 0.0298 nan 0.0500 0.0017
## 7 0.0280 nan 0.0500 0.0023
## 8 0.0269 nan 0.0500 0.0007
## 9 0.0251 nan 0.0500 0.0016
## 10 0.0242 nan 0.0500 0.0005
## 20 0.0141 nan 0.0500 0.0002
## 40 0.0060 nan 0.0500 0.0000
## 60 0.0026 nan 0.0500 -0.0000
## 80 0.0013 nan 0.0500 0.0000
## 100 0.0008 nan 0.0500 0.0000
## 120 0.0004 nan 0.0500 0.0000
## 140 0.0003 nan 0.0500 0.0000
## 160 0.0002 nan 0.0500 -0.0000
## 180 0.0001 nan 0.0500 -0.0000
## 200 0.0001 nan 0.0500 -0.0000
##
## - Fold06: shrinkage=0.05, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold06: shrinkage=0.05, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0400 nan 0.0500 0.0027
## 2 0.0374 nan 0.0500 0.0024
## 3 0.0353 nan 0.0500 0.0017
## 4 0.0327 nan 0.0500 0.0021
## 5 0.0302 nan 0.0500 0.0020
## 6 0.0279 nan 0.0500 0.0023
## 7 0.0262 nan 0.0500 0.0013
## 8 0.0256 nan 0.0500 -0.0004
## 9 0.0253 nan 0.0500 -0.0003
## 10 0.0234 nan 0.0500 0.0006
## 20 0.0143 nan 0.0500 0.0007
## 40 0.0058 nan 0.0500 0.0001
## 60 0.0030 nan 0.0500 -0.0000
## 80 0.0017 nan 0.0500 0.0000
## 100 0.0009 nan 0.0500 -0.0000
## 120 0.0006 nan 0.0500 -0.0000
## 140 0.0004 nan 0.0500 -0.0000
## 160 0.0002 nan 0.0500 -0.0000
## 180 0.0002 nan 0.0500 0.0000
## 200 0.0001 nan 0.0500 -0.0000
##
## - Fold06: shrinkage=0.05, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold06: shrinkage=0.05, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0402 nan 0.0500 0.0023
## 2 0.0375 nan 0.0500 0.0026
## 3 0.0351 nan 0.0500 0.0021
## 4 0.0332 nan 0.0500 0.0021
## 5 0.0317 nan 0.0500 0.0016
## 6 0.0297 nan 0.0500 0.0020
## 7 0.0280 nan 0.0500 0.0017
## 8 0.0260 nan 0.0500 0.0011
## 9 0.0246 nan 0.0500 0.0013
## 10 0.0234 nan 0.0500 0.0008
## 20 0.0155 nan 0.0500 0.0003
## 40 0.0090 nan 0.0500 -0.0003
## 60 0.0053 nan 0.0500 -0.0001
## 80 0.0036 nan 0.0500 -0.0000
## 100 0.0022 nan 0.0500 -0.0000
## 120 0.0018 nan 0.0500 -0.0000
## 140 0.0013 nan 0.0500 -0.0000
## 160 0.0010 nan 0.0500 -0.0000
## 180 0.0007 nan 0.0500 0.0000
## 200 0.0005 nan 0.0500 -0.0000
##
## - Fold06: shrinkage=0.05, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold06: shrinkage=0.05, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0395 nan 0.0500 0.0013
## 2 0.0383 nan 0.0500 -0.0002
## 3 0.0359 nan 0.0500 0.0017
## 4 0.0331 nan 0.0500 0.0021
## 5 0.0308 nan 0.0500 0.0016
## 6 0.0299 nan 0.0500 0.0006
## 7 0.0281 nan 0.0500 0.0013
## 8 0.0259 nan 0.0500 0.0017
## 9 0.0250 nan 0.0500 0.0009
## 10 0.0236 nan 0.0500 0.0011
## 20 0.0127 nan 0.0500 0.0008
## 40 0.0044 nan 0.0500 0.0002
## 60 0.0015 nan 0.0500 0.0001
## 80 0.0007 nan 0.0500 0.0000
## 100 0.0003 nan 0.0500 0.0000
## 120 0.0002 nan 0.0500 -0.0000
## 140 0.0001 nan 0.0500 -0.0000
## 160 0.0000 nan 0.0500 -0.0000
## 180 0.0000 nan 0.0500 0.0000
## 200 0.0000 nan 0.0500 -0.0000
##
## - Fold06: shrinkage=0.05, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold06: shrinkage=0.05, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0419 nan 0.0500 0.0005
## 2 0.0390 nan 0.0500 0.0017
## 3 0.0368 nan 0.0500 0.0016
## 4 0.0339 nan 0.0500 0.0012
## 5 0.0321 nan 0.0500 0.0002
## 6 0.0294 nan 0.0500 0.0012
## 7 0.0275 nan 0.0500 0.0012
## 8 0.0251 nan 0.0500 0.0019
## 9 0.0243 nan 0.0500 0.0003
## 10 0.0227 nan 0.0500 0.0013
## 20 0.0142 nan 0.0500 0.0005
## 40 0.0055 nan 0.0500 -0.0000
## 60 0.0025 nan 0.0500 0.0000
## 80 0.0011 nan 0.0500 -0.0000
## 100 0.0006 nan 0.0500 -0.0000
## 120 0.0003 nan 0.0500 0.0000
## 140 0.0002 nan 0.0500 -0.0000
## 160 0.0001 nan 0.0500 -0.0000
## 180 0.0001 nan 0.0500 -0.0000
## 200 0.0000 nan 0.0500 -0.0000
##
## - Fold06: shrinkage=0.05, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold06: shrinkage=0.05, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0402 nan 0.0500 0.0030
## 2 0.0374 nan 0.0500 0.0009
## 3 0.0360 nan 0.0500 0.0013
## 4 0.0334 nan 0.0500 0.0018
## 5 0.0319 nan 0.0500 0.0001
## 6 0.0298 nan 0.0500 0.0017
## 7 0.0285 nan 0.0500 0.0009
## 8 0.0270 nan 0.0500 0.0010
## 9 0.0255 nan 0.0500 0.0017
## 10 0.0241 nan 0.0500 0.0015
## 20 0.0151 nan 0.0500 0.0002
## 40 0.0087 nan 0.0500 -0.0001
## 60 0.0056 nan 0.0500 0.0000
## 80 0.0035 nan 0.0500 0.0000
## 100 0.0024 nan 0.0500 -0.0001
## 120 0.0018 nan 0.0500 0.0000
## 140 0.0013 nan 0.0500 0.0000
## 160 0.0011 nan 0.0500 -0.0000
## 180 0.0008 nan 0.0500 -0.0000
## 200 0.0007 nan 0.0500 -0.0000
##
## - Fold06: shrinkage=0.05, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold06: shrinkage=0.05, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0416 nan 0.0500 0.0015
## 2 0.0387 nan 0.0500 0.0032
## 3 0.0372 nan 0.0500 -0.0006
## 4 0.0348 nan 0.0500 0.0021
## 5 0.0337 nan 0.0500 -0.0001
## 6 0.0317 nan 0.0500 0.0007
## 7 0.0301 nan 0.0500 0.0005
## 8 0.0281 nan 0.0500 0.0005
## 9 0.0260 nan 0.0500 0.0017
## 10 0.0237 nan 0.0500 0.0009
## 20 0.0121 nan 0.0500 0.0006
## 40 0.0036 nan 0.0500 0.0001
## 60 0.0013 nan 0.0500 -0.0001
## 80 0.0006 nan 0.0500 0.0000
## 100 0.0003 nan 0.0500 -0.0000
## 120 0.0001 nan 0.0500 0.0000
## 140 0.0001 nan 0.0500 -0.0000
## 160 0.0000 nan 0.0500 -0.0000
## 180 0.0000 nan 0.0500 -0.0000
## 200 0.0000 nan 0.0500 -0.0000
##
## - Fold06: shrinkage=0.05, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold06: shrinkage=0.05, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0401 nan 0.0500 0.0023
## 2 0.0365 nan 0.0500 0.0027
## 3 0.0345 nan 0.0500 0.0005
## 4 0.0320 nan 0.0500 0.0016
## 5 0.0299 nan 0.0500 0.0020
## 6 0.0283 nan 0.0500 0.0007
## 7 0.0270 nan 0.0500 0.0006
## 8 0.0252 nan 0.0500 0.0017
## 9 0.0234 nan 0.0500 0.0016
## 10 0.0213 nan 0.0500 0.0015
## 20 0.0108 nan 0.0500 0.0008
## 40 0.0037 nan 0.0500 0.0001
## 60 0.0016 nan 0.0500 0.0000
## 80 0.0008 nan 0.0500 -0.0000
## 100 0.0005 nan 0.0500 -0.0000
## 120 0.0003 nan 0.0500 -0.0000
## 140 0.0002 nan 0.0500 -0.0000
## 160 0.0001 nan 0.0500 0.0000
## 180 0.0001 nan 0.0500 -0.0000
## 200 0.0001 nan 0.0500 -0.0000
##
## - Fold06: shrinkage=0.05, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold06: shrinkage=0.05, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0406 nan 0.0500 0.0027
## 2 0.0392 nan 0.0500 0.0001
## 3 0.0365 nan 0.0500 0.0019
## 4 0.0348 nan 0.0500 0.0017
## 5 0.0328 nan 0.0500 0.0015
## 6 0.0308 nan 0.0500 0.0016
## 7 0.0294 nan 0.0500 0.0014
## 8 0.0287 nan 0.0500 0.0005
## 9 0.0271 nan 0.0500 0.0003
## 10 0.0254 nan 0.0500 0.0014
## 20 0.0163 nan 0.0500 0.0007
## 40 0.0079 nan 0.0500 0.0002
## 60 0.0044 nan 0.0500 0.0000
## 80 0.0028 nan 0.0500 -0.0000
## 100 0.0019 nan 0.0500 0.0000
## 120 0.0014 nan 0.0500 -0.0000
## 140 0.0010 nan 0.0500 -0.0000
## 160 0.0008 nan 0.0500 -0.0000
## 180 0.0005 nan 0.0500 -0.0000
## 200 0.0004 nan 0.0500 0.0000
##
## - Fold06: shrinkage=0.05, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold06: shrinkage=0.10, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0378 nan 0.1000 0.0055
## 2 0.0338 nan 0.1000 0.0043
## 3 0.0285 nan 0.1000 0.0037
## 4 0.0256 nan 0.1000 0.0012
## 5 0.0227 nan 0.1000 0.0024
## 6 0.0206 nan 0.1000 0.0025
## 7 0.0186 nan 0.1000 0.0019
## 8 0.0164 nan 0.1000 0.0011
## 9 0.0149 nan 0.1000 0.0011
## 10 0.0140 nan 0.1000 0.0005
## 20 0.0068 nan 0.1000 0.0001
## 40 0.0015 nan 0.1000 -0.0000
## 60 0.0005 nan 0.1000 -0.0000
## 80 0.0002 nan 0.1000 0.0000
## 100 0.0001 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold06: shrinkage=0.10, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold06: shrinkage=0.10, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0380 nan 0.1000 0.0050
## 2 0.0333 nan 0.1000 0.0047
## 3 0.0289 nan 0.1000 0.0037
## 4 0.0260 nan 0.1000 0.0025
## 5 0.0229 nan 0.1000 0.0020
## 6 0.0200 nan 0.1000 0.0016
## 7 0.0177 nan 0.1000 0.0017
## 8 0.0164 nan 0.1000 0.0014
## 9 0.0147 nan 0.1000 0.0015
## 10 0.0133 nan 0.1000 -0.0003
## 20 0.0063 nan 0.1000 0.0001
## 40 0.0022 nan 0.1000 0.0000
## 60 0.0010 nan 0.1000 -0.0001
## 80 0.0004 nan 0.1000 -0.0000
## 100 0.0002 nan 0.1000 0.0000
## 120 0.0001 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold06: shrinkage=0.10, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold06: shrinkage=0.10, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0374 nan 0.1000 0.0056
## 2 0.0333 nan 0.1000 0.0022
## 3 0.0296 nan 0.1000 0.0037
## 4 0.0269 nan 0.1000 0.0025
## 5 0.0248 nan 0.1000 0.0022
## 6 0.0229 nan 0.1000 0.0014
## 7 0.0213 nan 0.1000 0.0002
## 8 0.0191 nan 0.1000 0.0017
## 9 0.0180 nan 0.1000 0.0008
## 10 0.0155 nan 0.1000 0.0015
## 20 0.0077 nan 0.1000 -0.0000
## 40 0.0037 nan 0.1000 0.0001
## 60 0.0018 nan 0.1000 0.0001
## 80 0.0010 nan 0.1000 -0.0000
## 100 0.0006 nan 0.1000 -0.0000
## 120 0.0003 nan 0.1000 0.0000
## 140 0.0003 nan 0.1000 -0.0000
## 160 0.0002 nan 0.1000 -0.0000
## 180 0.0001 nan 0.1000 -0.0000
## 200 0.0001 nan 0.1000 -0.0000
##
## - Fold06: shrinkage=0.10, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold06: shrinkage=0.10, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0362 nan 0.1000 0.0058
## 2 0.0306 nan 0.1000 0.0040
## 3 0.0257 nan 0.1000 0.0056
## 4 0.0237 nan 0.1000 0.0023
## 5 0.0212 nan 0.1000 0.0022
## 6 0.0186 nan 0.1000 0.0021
## 7 0.0165 nan 0.1000 0.0020
## 8 0.0145 nan 0.1000 0.0011
## 9 0.0126 nan 0.1000 0.0015
## 10 0.0117 nan 0.1000 0.0005
## 20 0.0037 nan 0.1000 0.0001
## 40 0.0008 nan 0.1000 -0.0000
## 60 0.0002 nan 0.1000 0.0000
## 80 0.0001 nan 0.1000 -0.0000
## 100 0.0000 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold06: shrinkage=0.10, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold06: shrinkage=0.10, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0378 nan 0.1000 0.0041
## 2 0.0330 nan 0.1000 0.0040
## 3 0.0281 nan 0.1000 0.0042
## 4 0.0249 nan 0.1000 0.0028
## 5 0.0233 nan 0.1000 0.0014
## 6 0.0217 nan 0.1000 -0.0001
## 7 0.0202 nan 0.1000 -0.0000
## 8 0.0181 nan 0.1000 0.0007
## 9 0.0164 nan 0.1000 0.0010
## 10 0.0149 nan 0.1000 0.0010
## 20 0.0051 nan 0.1000 0.0003
## 40 0.0017 nan 0.1000 0.0001
## 60 0.0004 nan 0.1000 0.0000
## 80 0.0002 nan 0.1000 0.0000
## 100 0.0001 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold06: shrinkage=0.10, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold06: shrinkage=0.10, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0368 nan 0.1000 0.0055
## 2 0.0320 nan 0.1000 0.0045
## 3 0.0295 nan 0.1000 0.0017
## 4 0.0280 nan 0.1000 -0.0004
## 5 0.0267 nan 0.1000 0.0015
## 6 0.0244 nan 0.1000 0.0013
## 7 0.0224 nan 0.1000 0.0025
## 8 0.0210 nan 0.1000 0.0010
## 9 0.0184 nan 0.1000 0.0019
## 10 0.0163 nan 0.1000 0.0011
## 20 0.0083 nan 0.1000 0.0004
## 40 0.0044 nan 0.1000 -0.0001
## 60 0.0017 nan 0.1000 -0.0001
## 80 0.0008 nan 0.1000 -0.0000
## 100 0.0004 nan 0.1000 -0.0000
## 120 0.0002 nan 0.1000 0.0000
## 140 0.0001 nan 0.1000 -0.0000
## 160 0.0001 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold06: shrinkage=0.10, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold06: shrinkage=0.10, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0391 nan 0.1000 0.0016
## 2 0.0350 nan 0.1000 0.0018
## 3 0.0295 nan 0.1000 0.0040
## 4 0.0267 nan 0.1000 0.0030
## 5 0.0229 nan 0.1000 0.0015
## 6 0.0188 nan 0.1000 0.0033
## 7 0.0156 nan 0.1000 0.0023
## 8 0.0135 nan 0.1000 0.0007
## 9 0.0121 nan 0.1000 0.0010
## 10 0.0105 nan 0.1000 0.0007
## 20 0.0033 nan 0.1000 0.0003
## 40 0.0006 nan 0.1000 -0.0000
## 60 0.0001 nan 0.1000 0.0000
## 80 0.0000 nan 0.1000 -0.0000
## 100 0.0000 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 0.0000
## 200 0.0000 nan 0.1000 0.0000
##
## - Fold06: shrinkage=0.10, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold06: shrinkage=0.10, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0356 nan 0.1000 0.0040
## 2 0.0296 nan 0.1000 0.0032
## 3 0.0255 nan 0.1000 0.0029
## 4 0.0231 nan 0.1000 0.0021
## 5 0.0204 nan 0.1000 0.0028
## 6 0.0179 nan 0.1000 0.0011
## 7 0.0160 nan 0.1000 0.0016
## 8 0.0141 nan 0.1000 0.0014
## 9 0.0132 nan 0.1000 0.0007
## 10 0.0117 nan 0.1000 0.0008
## 20 0.0035 nan 0.1000 0.0002
## 40 0.0012 nan 0.1000 0.0000
## 60 0.0005 nan 0.1000 0.0000
## 80 0.0003 nan 0.1000 -0.0000
## 100 0.0001 nan 0.1000 0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold06: shrinkage=0.10, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold06: shrinkage=0.10, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0372 nan 0.1000 0.0030
## 2 0.0323 nan 0.1000 0.0021
## 3 0.0288 nan 0.1000 0.0038
## 4 0.0264 nan 0.1000 0.0014
## 5 0.0236 nan 0.1000 0.0006
## 6 0.0219 nan 0.1000 -0.0004
## 7 0.0214 nan 0.1000 -0.0008
## 8 0.0194 nan 0.1000 0.0024
## 9 0.0171 nan 0.1000 0.0021
## 10 0.0152 nan 0.1000 0.0016
## 20 0.0070 nan 0.1000 0.0006
## 40 0.0025 nan 0.1000 0.0000
## 60 0.0010 nan 0.1000 0.0000
## 80 0.0005 nan 0.1000 -0.0000
## 100 0.0003 nan 0.1000 0.0000
## 120 0.0002 nan 0.1000 -0.0000
## 140 0.0001 nan 0.1000 -0.0000
## 160 0.0001 nan 0.1000 -0.0000
## 180 0.0001 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold06: shrinkage=0.10, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold07: shrinkage=0.01, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0427 nan 0.0100 0.0001
## 2 0.0421 nan 0.0100 0.0004
## 3 0.0415 nan 0.0100 0.0004
## 4 0.0411 nan 0.0100 0.0000
## 5 0.0406 nan 0.0100 0.0006
## 6 0.0399 nan 0.0100 0.0001
## 7 0.0395 nan 0.0100 0.0003
## 8 0.0391 nan 0.0100 0.0002
## 9 0.0386 nan 0.0100 0.0002
## 10 0.0382 nan 0.0100 0.0003
## 20 0.0343 nan 0.0100 0.0002
## 40 0.0278 nan 0.0100 0.0000
## 60 0.0228 nan 0.0100 0.0002
## 80 0.0187 nan 0.0100 0.0001
## 100 0.0155 nan 0.0100 0.0001
## 120 0.0127 nan 0.0100 0.0001
## 140 0.0104 nan 0.0100 0.0000
## 160 0.0090 nan 0.0100 0.0000
## 180 0.0075 nan 0.0100 0.0000
## 200 0.0062 nan 0.0100 0.0001
##
## - Fold07: shrinkage=0.01, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold07: shrinkage=0.01, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0423 nan 0.0100 0.0006
## 2 0.0417 nan 0.0100 0.0005
## 3 0.0414 nan 0.0100 0.0001
## 4 0.0409 nan 0.0100 0.0005
## 5 0.0403 nan 0.0100 0.0002
## 6 0.0398 nan 0.0100 0.0004
## 7 0.0391 nan 0.0100 0.0005
## 8 0.0385 nan 0.0100 0.0005
## 9 0.0381 nan 0.0100 0.0004
## 10 0.0376 nan 0.0100 0.0004
## 20 0.0335 nan 0.0100 0.0001
## 40 0.0268 nan 0.0100 0.0001
## 60 0.0217 nan 0.0100 0.0002
## 80 0.0178 nan 0.0100 0.0002
## 100 0.0147 nan 0.0100 0.0001
## 120 0.0126 nan 0.0100 0.0000
## 140 0.0107 nan 0.0100 0.0001
## 160 0.0089 nan 0.0100 0.0001
## 180 0.0075 nan 0.0100 0.0000
## 200 0.0064 nan 0.0100 0.0000
##
## - Fold07: shrinkage=0.01, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold07: shrinkage=0.01, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0426 nan 0.0100 0.0000
## 2 0.0421 nan 0.0100 0.0005
## 3 0.0416 nan 0.0100 0.0006
## 4 0.0412 nan 0.0100 0.0005
## 5 0.0406 nan 0.0100 0.0003
## 6 0.0401 nan 0.0100 0.0006
## 7 0.0395 nan 0.0100 0.0004
## 8 0.0392 nan 0.0100 0.0001
## 9 0.0386 nan 0.0100 0.0005
## 10 0.0382 nan 0.0100 0.0003
## 20 0.0341 nan 0.0100 0.0004
## 40 0.0273 nan 0.0100 0.0002
## 60 0.0222 nan 0.0100 0.0001
## 80 0.0182 nan 0.0100 0.0000
## 100 0.0155 nan 0.0100 0.0001
## 120 0.0130 nan 0.0100 0.0001
## 140 0.0112 nan 0.0100 0.0001
## 160 0.0097 nan 0.0100 0.0001
## 180 0.0086 nan 0.0100 0.0000
## 200 0.0077 nan 0.0100 0.0000
##
## - Fold07: shrinkage=0.01, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold07: shrinkage=0.01, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0422 nan 0.0100 0.0005
## 2 0.0415 nan 0.0100 0.0007
## 3 0.0407 nan 0.0100 0.0006
## 4 0.0402 nan 0.0100 0.0002
## 5 0.0397 nan 0.0100 0.0002
## 6 0.0390 nan 0.0100 0.0008
## 7 0.0383 nan 0.0100 0.0005
## 8 0.0379 nan 0.0100 0.0003
## 9 0.0371 nan 0.0100 0.0007
## 10 0.0366 nan 0.0100 0.0002
## 20 0.0316 nan 0.0100 0.0003
## 40 0.0238 nan 0.0100 0.0004
## 60 0.0182 nan 0.0100 -0.0000
## 80 0.0142 nan 0.0100 0.0002
## 100 0.0113 nan 0.0100 0.0000
## 120 0.0088 nan 0.0100 0.0001
## 140 0.0070 nan 0.0100 0.0000
## 160 0.0056 nan 0.0100 0.0000
## 180 0.0044 nan 0.0100 0.0001
## 200 0.0037 nan 0.0100 -0.0000
##
## - Fold07: shrinkage=0.01, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold07: shrinkage=0.01, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0424 nan 0.0100 0.0003
## 2 0.0417 nan 0.0100 0.0007
## 3 0.0411 nan 0.0100 0.0004
## 4 0.0405 nan 0.0100 0.0003
## 5 0.0400 nan 0.0100 0.0004
## 6 0.0396 nan 0.0100 0.0004
## 7 0.0390 nan 0.0100 0.0004
## 8 0.0384 nan 0.0100 0.0002
## 9 0.0379 nan 0.0100 0.0004
## 10 0.0377 nan 0.0100 0.0001
## 20 0.0329 nan 0.0100 0.0005
## 40 0.0251 nan 0.0100 0.0002
## 60 0.0199 nan 0.0100 -0.0000
## 80 0.0154 nan 0.0100 0.0001
## 100 0.0122 nan 0.0100 0.0001
## 120 0.0097 nan 0.0100 0.0001
## 140 0.0081 nan 0.0100 -0.0000
## 160 0.0065 nan 0.0100 0.0000
## 180 0.0053 nan 0.0100 0.0000
## 200 0.0044 nan 0.0100 0.0000
##
## - Fold07: shrinkage=0.01, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold07: shrinkage=0.01, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0423 nan 0.0100 0.0006
## 2 0.0420 nan 0.0100 0.0002
## 3 0.0414 nan 0.0100 0.0005
## 4 0.0409 nan 0.0100 0.0002
## 5 0.0405 nan 0.0100 0.0003
## 6 0.0399 nan 0.0100 0.0006
## 7 0.0397 nan 0.0100 0.0001
## 8 0.0393 nan 0.0100 0.0002
## 9 0.0387 nan 0.0100 0.0005
## 10 0.0383 nan 0.0100 0.0005
## 20 0.0339 nan 0.0100 0.0003
## 40 0.0272 nan 0.0100 0.0001
## 60 0.0220 nan 0.0100 0.0002
## 80 0.0182 nan 0.0100 0.0001
## 100 0.0150 nan 0.0100 0.0001
## 120 0.0127 nan 0.0100 0.0000
## 140 0.0110 nan 0.0100 0.0000
## 160 0.0098 nan 0.0100 0.0000
## 180 0.0086 nan 0.0100 0.0000
## 200 0.0076 nan 0.0100 -0.0001
##
## - Fold07: shrinkage=0.01, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold07: shrinkage=0.01, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0422 nan 0.0100 0.0005
## 2 0.0416 nan 0.0100 0.0005
## 3 0.0412 nan 0.0100 0.0005
## 4 0.0406 nan 0.0100 0.0002
## 5 0.0399 nan 0.0100 0.0006
## 6 0.0394 nan 0.0100 0.0003
## 7 0.0388 nan 0.0100 0.0004
## 8 0.0383 nan 0.0100 0.0003
## 9 0.0376 nan 0.0100 0.0005
## 10 0.0372 nan 0.0100 0.0001
## 20 0.0319 nan 0.0100 0.0002
## 40 0.0242 nan 0.0100 -0.0001
## 60 0.0184 nan 0.0100 0.0002
## 80 0.0140 nan 0.0100 0.0002
## 100 0.0109 nan 0.0100 0.0001
## 120 0.0084 nan 0.0100 0.0001
## 140 0.0067 nan 0.0100 -0.0000
## 160 0.0052 nan 0.0100 0.0000
## 180 0.0041 nan 0.0100 0.0000
## 200 0.0032 nan 0.0100 0.0000
##
## - Fold07: shrinkage=0.01, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold07: shrinkage=0.01, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0423 nan 0.0100 0.0005
## 2 0.0417 nan 0.0100 0.0005
## 3 0.0412 nan 0.0100 0.0006
## 4 0.0407 nan 0.0100 0.0001
## 5 0.0401 nan 0.0100 0.0005
## 6 0.0395 nan 0.0100 0.0004
## 7 0.0390 nan 0.0100 0.0004
## 8 0.0386 nan 0.0100 -0.0001
## 9 0.0382 nan 0.0100 0.0005
## 10 0.0379 nan 0.0100 0.0002
## 20 0.0337 nan 0.0100 0.0004
## 40 0.0256 nan 0.0100 0.0003
## 60 0.0195 nan 0.0100 0.0000
## 80 0.0150 nan 0.0100 0.0002
## 100 0.0118 nan 0.0100 0.0001
## 120 0.0091 nan 0.0100 0.0001
## 140 0.0073 nan 0.0100 -0.0000
## 160 0.0057 nan 0.0100 0.0000
## 180 0.0047 nan 0.0100 0.0000
## 200 0.0038 nan 0.0100 -0.0000
##
## - Fold07: shrinkage=0.01, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold07: shrinkage=0.01, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0423 nan 0.0100 0.0002
## 2 0.0419 nan 0.0100 0.0004
## 3 0.0413 nan 0.0100 0.0006
## 4 0.0407 nan 0.0100 0.0005
## 5 0.0403 nan 0.0100 0.0003
## 6 0.0399 nan 0.0100 0.0001
## 7 0.0394 nan 0.0100 0.0002
## 8 0.0388 nan 0.0100 0.0004
## 9 0.0384 nan 0.0100 0.0005
## 10 0.0379 nan 0.0100 0.0005
## 20 0.0337 nan 0.0100 0.0004
## 40 0.0271 nan 0.0100 0.0003
## 60 0.0220 nan 0.0100 0.0002
## 80 0.0186 nan 0.0100 0.0002
## 100 0.0154 nan 0.0100 0.0001
## 120 0.0131 nan 0.0100 0.0001
## 140 0.0115 nan 0.0100 -0.0000
## 160 0.0100 nan 0.0100 -0.0000
## 180 0.0088 nan 0.0100 0.0000
## 200 0.0080 nan 0.0100 -0.0000
##
## - Fold07: shrinkage=0.01, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold07: shrinkage=0.05, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0413 nan 0.0500 0.0005
## 2 0.0378 nan 0.0500 0.0025
## 3 0.0353 nan 0.0500 0.0017
## 4 0.0335 nan 0.0500 0.0019
## 5 0.0314 nan 0.0500 0.0017
## 6 0.0298 nan 0.0500 0.0002
## 7 0.0277 nan 0.0500 0.0022
## 8 0.0262 nan 0.0500 0.0006
## 9 0.0244 nan 0.0500 0.0010
## 10 0.0229 nan 0.0500 0.0014
## 20 0.0135 nan 0.0500 0.0005
## 40 0.0055 nan 0.0500 0.0000
## 60 0.0026 nan 0.0500 0.0000
## 80 0.0014 nan 0.0500 0.0000
## 100 0.0008 nan 0.0500 0.0000
## 120 0.0005 nan 0.0500 -0.0000
## 140 0.0003 nan 0.0500 -0.0000
## 160 0.0002 nan 0.0500 0.0000
## 180 0.0001 nan 0.0500 -0.0000
## 200 0.0001 nan 0.0500 -0.0000
##
## - Fold07: shrinkage=0.05, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold07: shrinkage=0.05, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0418 nan 0.0500 -0.0005
## 2 0.0388 nan 0.0500 0.0021
## 3 0.0366 nan 0.0500 0.0016
## 4 0.0340 nan 0.0500 0.0018
## 5 0.0319 nan 0.0500 0.0018
## 6 0.0296 nan 0.0500 0.0019
## 7 0.0275 nan 0.0500 0.0014
## 8 0.0266 nan 0.0500 -0.0007
## 9 0.0252 nan 0.0500 0.0006
## 10 0.0240 nan 0.0500 0.0007
## 20 0.0143 nan 0.0500 0.0008
## 40 0.0057 nan 0.0500 0.0002
## 60 0.0027 nan 0.0500 -0.0000
## 80 0.0017 nan 0.0500 -0.0001
## 100 0.0009 nan 0.0500 -0.0000
## 120 0.0006 nan 0.0500 0.0000
## 140 0.0004 nan 0.0500 -0.0000
## 160 0.0002 nan 0.0500 -0.0000
## 180 0.0002 nan 0.0500 -0.0000
## 200 0.0001 nan 0.0500 -0.0000
##
## - Fold07: shrinkage=0.05, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold07: shrinkage=0.05, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0401 nan 0.0500 0.0029
## 2 0.0383 nan 0.0500 0.0002
## 3 0.0358 nan 0.0500 0.0017
## 4 0.0334 nan 0.0500 0.0020
## 5 0.0312 nan 0.0500 0.0020
## 6 0.0293 nan 0.0500 0.0017
## 7 0.0279 nan 0.0500 0.0016
## 8 0.0268 nan 0.0500 0.0011
## 9 0.0252 nan 0.0500 0.0014
## 10 0.0244 nan 0.0500 0.0003
## 20 0.0150 nan 0.0500 0.0007
## 40 0.0073 nan 0.0500 0.0001
## 60 0.0045 nan 0.0500 0.0000
## 80 0.0026 nan 0.0500 0.0000
## 100 0.0018 nan 0.0500 -0.0001
## 120 0.0012 nan 0.0500 0.0000
## 140 0.0009 nan 0.0500 -0.0000
## 160 0.0006 nan 0.0500 -0.0000
## 180 0.0005 nan 0.0500 -0.0000
## 200 0.0004 nan 0.0500 0.0000
##
## - Fold07: shrinkage=0.05, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold07: shrinkage=0.05, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0401 nan 0.0500 0.0029
## 2 0.0367 nan 0.0500 0.0029
## 3 0.0351 nan 0.0500 0.0003
## 4 0.0330 nan 0.0500 0.0018
## 5 0.0306 nan 0.0500 0.0015
## 6 0.0291 nan 0.0500 0.0003
## 7 0.0264 nan 0.0500 0.0032
## 8 0.0247 nan 0.0500 0.0013
## 9 0.0226 nan 0.0500 0.0015
## 10 0.0206 nan 0.0500 0.0025
## 20 0.0108 nan 0.0500 0.0003
## 40 0.0038 nan 0.0500 -0.0001
## 60 0.0017 nan 0.0500 0.0000
## 80 0.0009 nan 0.0500 -0.0000
## 100 0.0004 nan 0.0500 -0.0000
## 120 0.0002 nan 0.0500 -0.0000
## 140 0.0001 nan 0.0500 0.0000
## 160 0.0001 nan 0.0500 -0.0000
## 180 0.0000 nan 0.0500 0.0000
## 200 0.0000 nan 0.0500 -0.0000
##
## - Fold07: shrinkage=0.05, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold07: shrinkage=0.05, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0400 nan 0.0500 0.0023
## 2 0.0371 nan 0.0500 0.0025
## 3 0.0342 nan 0.0500 0.0020
## 4 0.0324 nan 0.0500 0.0017
## 5 0.0295 nan 0.0500 0.0026
## 6 0.0275 nan 0.0500 0.0014
## 7 0.0258 nan 0.0500 0.0014
## 8 0.0240 nan 0.0500 0.0018
## 9 0.0226 nan 0.0500 0.0011
## 10 0.0219 nan 0.0500 0.0001
## 20 0.0123 nan 0.0500 -0.0005
## 40 0.0041 nan 0.0500 0.0002
## 60 0.0018 nan 0.0500 0.0001
## 80 0.0010 nan 0.0500 0.0000
## 100 0.0005 nan 0.0500 -0.0000
## 120 0.0003 nan 0.0500 -0.0000
## 140 0.0002 nan 0.0500 -0.0000
## 160 0.0001 nan 0.0500 -0.0000
## 180 0.0001 nan 0.0500 -0.0000
## 200 0.0000 nan 0.0500 -0.0000
##
## - Fold07: shrinkage=0.05, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold07: shrinkage=0.05, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0399 nan 0.0500 0.0028
## 2 0.0372 nan 0.0500 0.0017
## 3 0.0340 nan 0.0500 0.0021
## 4 0.0322 nan 0.0500 0.0020
## 5 0.0300 nan 0.0500 0.0016
## 6 0.0284 nan 0.0500 0.0010
## 7 0.0270 nan 0.0500 0.0014
## 8 0.0258 nan 0.0500 0.0004
## 9 0.0246 nan 0.0500 0.0004
## 10 0.0232 nan 0.0500 0.0013
## 20 0.0161 nan 0.0500 0.0007
## 40 0.0078 nan 0.0500 0.0001
## 60 0.0052 nan 0.0500 0.0001
## 80 0.0034 nan 0.0500 0.0000
## 100 0.0020 nan 0.0500 -0.0000
## 120 0.0014 nan 0.0500 -0.0000
## 140 0.0009 nan 0.0500 0.0000
## 160 0.0006 nan 0.0500 -0.0000
## 180 0.0004 nan 0.0500 0.0000
## 200 0.0003 nan 0.0500 -0.0000
##
## - Fold07: shrinkage=0.05, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold07: shrinkage=0.05, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0397 nan 0.0500 0.0019
## 2 0.0364 nan 0.0500 0.0021
## 3 0.0338 nan 0.0500 0.0022
## 4 0.0306 nan 0.0500 0.0029
## 5 0.0282 nan 0.0500 0.0015
## 6 0.0259 nan 0.0500 0.0011
## 7 0.0249 nan 0.0500 0.0011
## 8 0.0239 nan 0.0500 0.0004
## 9 0.0222 nan 0.0500 0.0006
## 10 0.0208 nan 0.0500 0.0014
## 20 0.0105 nan 0.0500 0.0007
## 40 0.0031 nan 0.0500 0.0001
## 60 0.0012 nan 0.0500 -0.0000
## 80 0.0005 nan 0.0500 0.0000
## 100 0.0002 nan 0.0500 -0.0000
## 120 0.0001 nan 0.0500 -0.0000
## 140 0.0000 nan 0.0500 0.0000
## 160 0.0000 nan 0.0500 0.0000
## 180 0.0000 nan 0.0500 -0.0000
## 200 0.0000 nan 0.0500 0.0000
##
## - Fold07: shrinkage=0.05, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold07: shrinkage=0.05, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0402 nan 0.0500 0.0030
## 2 0.0382 nan 0.0500 0.0015
## 3 0.0354 nan 0.0500 0.0028
## 4 0.0328 nan 0.0500 0.0014
## 5 0.0301 nan 0.0500 0.0025
## 6 0.0274 nan 0.0500 0.0022
## 7 0.0254 nan 0.0500 0.0016
## 8 0.0241 nan 0.0500 0.0011
## 9 0.0226 nan 0.0500 0.0005
## 10 0.0213 nan 0.0500 0.0016
## 20 0.0103 nan 0.0500 0.0005
## 40 0.0033 nan 0.0500 0.0001
## 60 0.0015 nan 0.0500 -0.0000
## 80 0.0007 nan 0.0500 0.0000
## 100 0.0004 nan 0.0500 0.0000
## 120 0.0002 nan 0.0500 -0.0000
## 140 0.0002 nan 0.0500 -0.0000
## 160 0.0001 nan 0.0500 0.0000
## 180 0.0001 nan 0.0500 -0.0000
## 200 0.0001 nan 0.0500 -0.0000
##
## - Fold07: shrinkage=0.05, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold07: shrinkage=0.05, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0409 nan 0.0500 0.0008
## 2 0.0388 nan 0.0500 0.0020
## 3 0.0365 nan 0.0500 0.0017
## 4 0.0341 nan 0.0500 0.0013
## 5 0.0325 nan 0.0500 0.0014
## 6 0.0321 nan 0.0500 -0.0003
## 7 0.0302 nan 0.0500 0.0019
## 8 0.0281 nan 0.0500 0.0019
## 9 0.0261 nan 0.0500 0.0011
## 10 0.0245 nan 0.0500 0.0013
## 20 0.0157 nan 0.0500 0.0002
## 40 0.0079 nan 0.0500 0.0001
## 60 0.0044 nan 0.0500 0.0000
## 80 0.0031 nan 0.0500 0.0000
## 100 0.0022 nan 0.0500 -0.0000
## 120 0.0016 nan 0.0500 -0.0000
## 140 0.0011 nan 0.0500 -0.0000
## 160 0.0009 nan 0.0500 -0.0000
## 180 0.0007 nan 0.0500 -0.0000
## 200 0.0005 nan 0.0500 -0.0000
##
## - Fold07: shrinkage=0.05, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold07: shrinkage=0.10, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0372 nan 0.1000 0.0058
## 2 0.0338 nan 0.1000 0.0028
## 3 0.0285 nan 0.1000 0.0041
## 4 0.0246 nan 0.1000 0.0037
## 5 0.0230 nan 0.1000 0.0016
## 6 0.0202 nan 0.1000 0.0024
## 7 0.0179 nan 0.1000 0.0008
## 8 0.0157 nan 0.1000 0.0025
## 9 0.0154 nan 0.1000 -0.0005
## 10 0.0138 nan 0.1000 0.0009
## 20 0.0055 nan 0.1000 0.0002
## 40 0.0014 nan 0.1000 -0.0000
## 60 0.0006 nan 0.1000 0.0000
## 80 0.0002 nan 0.1000 0.0000
## 100 0.0001 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold07: shrinkage=0.10, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold07: shrinkage=0.10, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0373 nan 0.1000 0.0054
## 2 0.0334 nan 0.1000 0.0018
## 3 0.0312 nan 0.1000 0.0023
## 4 0.0298 nan 0.1000 -0.0011
## 5 0.0275 nan 0.1000 0.0016
## 6 0.0247 nan 0.1000 0.0026
## 7 0.0220 nan 0.1000 0.0003
## 8 0.0199 nan 0.1000 0.0009
## 9 0.0179 nan 0.1000 0.0014
## 10 0.0170 nan 0.1000 0.0008
## 20 0.0079 nan 0.1000 0.0003
## 40 0.0025 nan 0.1000 -0.0001
## 60 0.0010 nan 0.1000 -0.0001
## 80 0.0004 nan 0.1000 0.0000
## 100 0.0001 nan 0.1000 0.0000
## 120 0.0001 nan 0.1000 0.0000
## 140 0.0000 nan 0.1000 0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold07: shrinkage=0.10, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold07: shrinkage=0.10, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0377 nan 0.1000 0.0051
## 2 0.0346 nan 0.1000 0.0021
## 3 0.0308 nan 0.1000 0.0041
## 4 0.0273 nan 0.1000 0.0034
## 5 0.0253 nan 0.1000 0.0013
## 6 0.0222 nan 0.1000 0.0024
## 7 0.0195 nan 0.1000 0.0014
## 8 0.0177 nan 0.1000 0.0007
## 9 0.0170 nan 0.1000 -0.0002
## 10 0.0157 nan 0.1000 0.0010
## 20 0.0090 nan 0.1000 -0.0005
## 40 0.0038 nan 0.1000 -0.0001
## 60 0.0017 nan 0.1000 -0.0001
## 80 0.0011 nan 0.1000 -0.0000
## 100 0.0006 nan 0.1000 -0.0000
## 120 0.0004 nan 0.1000 -0.0000
## 140 0.0002 nan 0.1000 0.0000
## 160 0.0001 nan 0.1000 0.0000
## 180 0.0001 nan 0.1000 -0.0000
## 200 0.0001 nan 0.1000 0.0000
##
## - Fold07: shrinkage=0.10, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold07: shrinkage=0.10, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0366 nan 0.1000 0.0043
## 2 0.0308 nan 0.1000 0.0056
## 3 0.0251 nan 0.1000 0.0031
## 4 0.0215 nan 0.1000 0.0017
## 5 0.0198 nan 0.1000 0.0007
## 6 0.0185 nan 0.1000 -0.0003
## 7 0.0159 nan 0.1000 0.0012
## 8 0.0133 nan 0.1000 0.0012
## 9 0.0113 nan 0.1000 0.0014
## 10 0.0103 nan 0.1000 0.0005
## 20 0.0031 nan 0.1000 -0.0000
## 40 0.0004 nan 0.1000 -0.0000
## 60 0.0001 nan 0.1000 -0.0000
## 80 0.0000 nan 0.1000 -0.0000
## 100 0.0000 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 0.0000
## 140 0.0000 nan 0.1000 0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold07: shrinkage=0.10, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold07: shrinkage=0.10, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0388 nan 0.1000 0.0032
## 2 0.0331 nan 0.1000 0.0043
## 3 0.0289 nan 0.1000 0.0029
## 4 0.0253 nan 0.1000 0.0033
## 5 0.0224 nan 0.1000 0.0029
## 6 0.0190 nan 0.1000 0.0027
## 7 0.0169 nan 0.1000 0.0021
## 8 0.0141 nan 0.1000 0.0013
## 9 0.0125 nan 0.1000 0.0019
## 10 0.0115 nan 0.1000 0.0007
## 20 0.0037 nan 0.1000 0.0000
## 40 0.0009 nan 0.1000 -0.0000
## 60 0.0003 nan 0.1000 -0.0000
## 80 0.0002 nan 0.1000 0.0000
## 100 0.0001 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold07: shrinkage=0.10, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold07: shrinkage=0.10, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0385 nan 0.1000 0.0016
## 2 0.0345 nan 0.1000 0.0032
## 3 0.0312 nan 0.1000 0.0043
## 4 0.0289 nan 0.1000 -0.0000
## 5 0.0263 nan 0.1000 0.0015
## 6 0.0221 nan 0.1000 0.0028
## 7 0.0199 nan 0.1000 0.0014
## 8 0.0171 nan 0.1000 0.0017
## 9 0.0155 nan 0.1000 0.0008
## 10 0.0141 nan 0.1000 0.0011
## 20 0.0075 nan 0.1000 0.0005
## 40 0.0028 nan 0.1000 0.0001
## 60 0.0014 nan 0.1000 -0.0000
## 80 0.0007 nan 0.1000 0.0000
## 100 0.0004 nan 0.1000 -0.0000
## 120 0.0003 nan 0.1000 -0.0000
## 140 0.0002 nan 0.1000 -0.0000
## 160 0.0001 nan 0.1000 0.0000
## 180 0.0001 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold07: shrinkage=0.10, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold07: shrinkage=0.10, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0349 nan 0.1000 0.0055
## 2 0.0293 nan 0.1000 0.0067
## 3 0.0251 nan 0.1000 0.0029
## 4 0.0213 nan 0.1000 0.0042
## 5 0.0200 nan 0.1000 0.0003
## 6 0.0173 nan 0.1000 0.0026
## 7 0.0148 nan 0.1000 0.0024
## 8 0.0132 nan 0.1000 0.0007
## 9 0.0115 nan 0.1000 0.0006
## 10 0.0093 nan 0.1000 0.0013
## 20 0.0028 nan 0.1000 0.0003
## 40 0.0004 nan 0.1000 -0.0000
## 60 0.0001 nan 0.1000 0.0000
## 80 0.0000 nan 0.1000 -0.0000
## 100 0.0000 nan 0.1000 0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold07: shrinkage=0.10, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold07: shrinkage=0.10, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0374 nan 0.1000 0.0055
## 2 0.0325 nan 0.1000 0.0028
## 3 0.0298 nan 0.1000 0.0022
## 4 0.0252 nan 0.1000 0.0036
## 5 0.0242 nan 0.1000 0.0000
## 6 0.0207 nan 0.1000 0.0026
## 7 0.0182 nan 0.1000 0.0013
## 8 0.0165 nan 0.1000 0.0012
## 9 0.0147 nan 0.1000 0.0004
## 10 0.0143 nan 0.1000 -0.0010
## 20 0.0056 nan 0.1000 0.0003
## 40 0.0011 nan 0.1000 0.0000
## 60 0.0002 nan 0.1000 -0.0000
## 80 0.0001 nan 0.1000 -0.0000
## 100 0.0001 nan 0.1000 0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold07: shrinkage=0.10, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold07: shrinkage=0.10, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0367 nan 0.1000 0.0053
## 2 0.0331 nan 0.1000 0.0018
## 3 0.0293 nan 0.1000 0.0038
## 4 0.0265 nan 0.1000 0.0030
## 5 0.0235 nan 0.1000 0.0018
## 6 0.0206 nan 0.1000 0.0025
## 7 0.0185 nan 0.1000 -0.0006
## 8 0.0160 nan 0.1000 0.0013
## 9 0.0143 nan 0.1000 0.0011
## 10 0.0137 nan 0.1000 -0.0011
## 20 0.0082 nan 0.1000 0.0002
## 40 0.0031 nan 0.1000 -0.0001
## 60 0.0016 nan 0.1000 0.0000
## 80 0.0009 nan 0.1000 -0.0000
## 100 0.0004 nan 0.1000 -0.0000
## 120 0.0003 nan 0.1000 -0.0000
## 140 0.0002 nan 0.1000 -0.0000
## 160 0.0001 nan 0.1000 0.0000
## 180 0.0001 nan 0.1000 0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold07: shrinkage=0.10, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold08: shrinkage=0.01, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0439 nan 0.0100 0.0004
## 2 0.0434 nan 0.0100 0.0003
## 3 0.0428 nan 0.0100 0.0003
## 4 0.0423 nan 0.0100 0.0005
## 5 0.0418 nan 0.0100 0.0002
## 6 0.0413 nan 0.0100 0.0002
## 7 0.0408 nan 0.0100 0.0006
## 8 0.0405 nan 0.0100 0.0001
## 9 0.0400 nan 0.0100 0.0003
## 10 0.0394 nan 0.0100 0.0006
## 20 0.0347 nan 0.0100 0.0001
## 40 0.0280 nan 0.0100 -0.0000
## 60 0.0223 nan 0.0100 0.0001
## 80 0.0179 nan 0.0100 0.0001
## 100 0.0147 nan 0.0100 0.0001
## 120 0.0121 nan 0.0100 0.0001
## 140 0.0101 nan 0.0100 0.0000
## 160 0.0084 nan 0.0100 0.0000
## 180 0.0071 nan 0.0100 0.0000
## 200 0.0061 nan 0.0100 0.0000
##
## - Fold08: shrinkage=0.01, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold08: shrinkage=0.01, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0438 nan 0.0100 0.0006
## 2 0.0433 nan 0.0100 0.0006
## 3 0.0427 nan 0.0100 0.0006
## 4 0.0420 nan 0.0100 0.0003
## 5 0.0413 nan 0.0100 0.0005
## 6 0.0408 nan 0.0100 0.0005
## 7 0.0403 nan 0.0100 0.0005
## 8 0.0398 nan 0.0100 0.0005
## 9 0.0394 nan 0.0100 0.0005
## 10 0.0389 nan 0.0100 0.0005
## 20 0.0346 nan 0.0100 0.0004
## 40 0.0275 nan 0.0100 0.0002
## 60 0.0224 nan 0.0100 0.0003
## 80 0.0186 nan 0.0100 -0.0000
## 100 0.0154 nan 0.0100 0.0000
## 120 0.0125 nan 0.0100 0.0001
## 140 0.0104 nan 0.0100 0.0000
## 160 0.0089 nan 0.0100 0.0001
## 180 0.0076 nan 0.0100 0.0000
## 200 0.0064 nan 0.0100 -0.0000
##
## - Fold08: shrinkage=0.01, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold08: shrinkage=0.01, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0440 nan 0.0100 0.0004
## 2 0.0435 nan 0.0100 0.0002
## 3 0.0428 nan 0.0100 0.0006
## 4 0.0423 nan 0.0100 0.0005
## 5 0.0417 nan 0.0100 0.0006
## 6 0.0410 nan 0.0100 0.0006
## 7 0.0404 nan 0.0100 0.0006
## 8 0.0400 nan 0.0100 0.0002
## 9 0.0396 nan 0.0100 0.0004
## 10 0.0390 nan 0.0100 0.0005
## 20 0.0345 nan 0.0100 0.0002
## 40 0.0275 nan 0.0100 0.0003
## 60 0.0222 nan 0.0100 0.0003
## 80 0.0186 nan 0.0100 0.0002
## 100 0.0158 nan 0.0100 -0.0001
## 120 0.0136 nan 0.0100 0.0001
## 140 0.0119 nan 0.0100 0.0000
## 160 0.0104 nan 0.0100 0.0001
## 180 0.0092 nan 0.0100 -0.0000
## 200 0.0081 nan 0.0100 0.0000
##
## - Fold08: shrinkage=0.01, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold08: shrinkage=0.01, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0437 nan 0.0100 0.0004
## 2 0.0429 nan 0.0100 0.0006
## 3 0.0422 nan 0.0100 0.0006
## 4 0.0414 nan 0.0100 0.0005
## 5 0.0407 nan 0.0100 0.0007
## 6 0.0403 nan 0.0100 0.0003
## 7 0.0399 nan 0.0100 0.0003
## 8 0.0396 nan 0.0100 0.0002
## 9 0.0392 nan 0.0100 0.0002
## 10 0.0389 nan 0.0100 -0.0002
## 20 0.0341 nan 0.0100 0.0004
## 40 0.0253 nan 0.0100 0.0002
## 60 0.0193 nan 0.0100 0.0000
## 80 0.0147 nan 0.0100 0.0002
## 100 0.0116 nan 0.0100 -0.0000
## 120 0.0092 nan 0.0100 0.0000
## 140 0.0073 nan 0.0100 0.0001
## 160 0.0057 nan 0.0100 0.0000
## 180 0.0046 nan 0.0100 0.0000
## 200 0.0037 nan 0.0100 0.0000
##
## - Fold08: shrinkage=0.01, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold08: shrinkage=0.01, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0439 nan 0.0100 0.0007
## 2 0.0431 nan 0.0100 0.0004
## 3 0.0424 nan 0.0100 0.0003
## 4 0.0418 nan 0.0100 0.0006
## 5 0.0414 nan 0.0100 0.0002
## 6 0.0412 nan 0.0100 -0.0001
## 7 0.0407 nan 0.0100 0.0006
## 8 0.0400 nan 0.0100 0.0005
## 9 0.0395 nan 0.0100 0.0005
## 10 0.0389 nan 0.0100 0.0006
## 20 0.0336 nan 0.0100 0.0001
## 40 0.0252 nan 0.0100 0.0001
## 60 0.0193 nan 0.0100 0.0002
## 80 0.0144 nan 0.0100 0.0002
## 100 0.0113 nan 0.0100 0.0001
## 120 0.0092 nan 0.0100 0.0001
## 140 0.0076 nan 0.0100 0.0000
## 160 0.0062 nan 0.0100 0.0001
## 180 0.0050 nan 0.0100 0.0000
## 200 0.0041 nan 0.0100 0.0000
##
## - Fold08: shrinkage=0.01, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold08: shrinkage=0.01, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0439 nan 0.0100 0.0005
## 2 0.0434 nan 0.0100 0.0006
## 3 0.0428 nan 0.0100 0.0004
## 4 0.0421 nan 0.0100 0.0006
## 5 0.0415 nan 0.0100 0.0004
## 6 0.0408 nan 0.0100 0.0006
## 7 0.0402 nan 0.0100 0.0005
## 8 0.0398 nan 0.0100 0.0003
## 9 0.0394 nan 0.0100 0.0003
## 10 0.0387 nan 0.0100 0.0006
## 20 0.0340 nan 0.0100 0.0004
## 40 0.0278 nan 0.0100 0.0001
## 60 0.0230 nan 0.0100 0.0003
## 80 0.0196 nan 0.0100 0.0001
## 100 0.0166 nan 0.0100 0.0001
## 120 0.0142 nan 0.0100 -0.0000
## 140 0.0121 nan 0.0100 0.0001
## 160 0.0105 nan 0.0100 0.0000
## 180 0.0093 nan 0.0100 0.0001
## 200 0.0083 nan 0.0100 0.0000
##
## - Fold08: shrinkage=0.01, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold08: shrinkage=0.01, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0435 nan 0.0100 0.0010
## 2 0.0428 nan 0.0100 0.0006
## 3 0.0424 nan 0.0100 0.0004
## 4 0.0416 nan 0.0100 0.0009
## 5 0.0412 nan 0.0100 0.0003
## 6 0.0404 nan 0.0100 0.0007
## 7 0.0402 nan 0.0100 -0.0001
## 8 0.0396 nan 0.0100 0.0004
## 9 0.0390 nan 0.0100 0.0003
## 10 0.0385 nan 0.0100 0.0005
## 20 0.0328 nan 0.0100 0.0004
## 40 0.0243 nan 0.0100 0.0001
## 60 0.0184 nan 0.0100 0.0002
## 80 0.0140 nan 0.0100 0.0001
## 100 0.0107 nan 0.0100 0.0001
## 120 0.0085 nan 0.0100 0.0000
## 140 0.0064 nan 0.0100 0.0001
## 160 0.0050 nan 0.0100 -0.0000
## 180 0.0039 nan 0.0100 0.0000
## 200 0.0031 nan 0.0100 0.0000
##
## - Fold08: shrinkage=0.01, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold08: shrinkage=0.01, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0436 nan 0.0100 0.0007
## 2 0.0428 nan 0.0100 0.0005
## 3 0.0420 nan 0.0100 0.0007
## 4 0.0413 nan 0.0100 0.0007
## 5 0.0406 nan 0.0100 0.0006
## 6 0.0401 nan 0.0100 0.0003
## 7 0.0396 nan 0.0100 0.0005
## 8 0.0390 nan 0.0100 0.0001
## 9 0.0385 nan 0.0100 0.0005
## 10 0.0381 nan 0.0100 0.0003
## 20 0.0335 nan 0.0100 0.0006
## 40 0.0257 nan 0.0100 0.0003
## 60 0.0195 nan 0.0100 0.0003
## 80 0.0151 nan 0.0100 0.0002
## 100 0.0119 nan 0.0100 0.0001
## 120 0.0093 nan 0.0100 0.0001
## 140 0.0075 nan 0.0100 0.0001
## 160 0.0060 nan 0.0100 0.0001
## 180 0.0050 nan 0.0100 0.0000
## 200 0.0041 nan 0.0100 -0.0000
##
## - Fold08: shrinkage=0.01, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold08: shrinkage=0.01, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0438 nan 0.0100 0.0006
## 2 0.0431 nan 0.0100 0.0005
## 3 0.0425 nan 0.0100 0.0004
## 4 0.0422 nan 0.0100 0.0003
## 5 0.0419 nan 0.0100 0.0000
## 6 0.0413 nan 0.0100 0.0005
## 7 0.0409 nan 0.0100 0.0001
## 8 0.0403 nan 0.0100 0.0006
## 9 0.0397 nan 0.0100 0.0004
## 10 0.0392 nan 0.0100 0.0005
## 20 0.0342 nan 0.0100 0.0005
## 40 0.0269 nan 0.0100 0.0002
## 60 0.0218 nan 0.0100 0.0002
## 80 0.0184 nan 0.0100 0.0001
## 100 0.0154 nan 0.0100 0.0000
## 120 0.0132 nan 0.0100 0.0001
## 140 0.0115 nan 0.0100 0.0000
## 160 0.0101 nan 0.0100 0.0000
## 180 0.0092 nan 0.0100 -0.0001
## 200 0.0081 nan 0.0100 0.0000
##
## - Fold08: shrinkage=0.01, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold08: shrinkage=0.05, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0413 nan 0.0500 0.0028
## 2 0.0388 nan 0.0500 0.0028
## 3 0.0365 nan 0.0500 0.0027
## 4 0.0340 nan 0.0500 0.0016
## 5 0.0317 nan 0.0500 0.0019
## 6 0.0300 nan 0.0500 0.0019
## 7 0.0284 nan 0.0500 0.0007
## 8 0.0266 nan 0.0500 0.0013
## 9 0.0252 nan 0.0500 0.0011
## 10 0.0237 nan 0.0500 0.0016
## 20 0.0135 nan 0.0500 0.0005
## 40 0.0060 nan 0.0500 0.0002
## 60 0.0028 nan 0.0500 0.0000
## 80 0.0016 nan 0.0500 0.0000
## 100 0.0009 nan 0.0500 -0.0000
## 120 0.0006 nan 0.0500 -0.0000
## 140 0.0004 nan 0.0500 -0.0000
## 160 0.0002 nan 0.0500 -0.0000
## 180 0.0002 nan 0.0500 -0.0000
## 200 0.0001 nan 0.0500 0.0000
##
## - Fold08: shrinkage=0.05, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold08: shrinkage=0.05, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0417 nan 0.0500 0.0032
## 2 0.0390 nan 0.0500 0.0032
## 3 0.0370 nan 0.0500 0.0016
## 4 0.0351 nan 0.0500 0.0013
## 5 0.0335 nan 0.0500 0.0019
## 6 0.0314 nan 0.0500 0.0010
## 7 0.0299 nan 0.0500 0.0018
## 8 0.0285 nan 0.0500 0.0001
## 9 0.0271 nan 0.0500 0.0014
## 10 0.0256 nan 0.0500 0.0014
## 20 0.0150 nan 0.0500 0.0008
## 40 0.0063 nan 0.0500 0.0002
## 60 0.0031 nan 0.0500 0.0001
## 80 0.0016 nan 0.0500 0.0000
## 100 0.0010 nan 0.0500 0.0000
## 120 0.0006 nan 0.0500 0.0000
## 140 0.0004 nan 0.0500 0.0000
## 160 0.0003 nan 0.0500 -0.0000
## 180 0.0002 nan 0.0500 -0.0000
## 200 0.0001 nan 0.0500 -0.0000
##
## - Fold08: shrinkage=0.05, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold08: shrinkage=0.05, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0415 nan 0.0500 0.0018
## 2 0.0381 nan 0.0500 0.0020
## 3 0.0361 nan 0.0500 0.0009
## 4 0.0341 nan 0.0500 0.0021
## 5 0.0319 nan 0.0500 0.0021
## 6 0.0300 nan 0.0500 0.0014
## 7 0.0277 nan 0.0500 0.0018
## 8 0.0266 nan 0.0500 0.0009
## 9 0.0249 nan 0.0500 0.0013
## 10 0.0240 nan 0.0500 0.0012
## 20 0.0161 nan 0.0500 0.0003
## 40 0.0075 nan 0.0500 0.0002
## 60 0.0051 nan 0.0500 0.0001
## 80 0.0032 nan 0.0500 -0.0001
## 100 0.0022 nan 0.0500 0.0000
## 120 0.0014 nan 0.0500 0.0000
## 140 0.0009 nan 0.0500 -0.0000
## 160 0.0006 nan 0.0500 -0.0000
## 180 0.0004 nan 0.0500 -0.0000
## 200 0.0003 nan 0.0500 -0.0000
##
## - Fold08: shrinkage=0.05, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold08: shrinkage=0.05, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0424 nan 0.0500 0.0011
## 2 0.0384 nan 0.0500 0.0037
## 3 0.0358 nan 0.0500 0.0027
## 4 0.0333 nan 0.0500 0.0026
## 5 0.0304 nan 0.0500 0.0025
## 6 0.0279 nan 0.0500 0.0020
## 7 0.0269 nan 0.0500 0.0005
## 8 0.0258 nan 0.0500 -0.0000
## 9 0.0239 nan 0.0500 0.0022
## 10 0.0219 nan 0.0500 0.0013
## 20 0.0114 nan 0.0500 0.0007
## 40 0.0034 nan 0.0500 0.0001
## 60 0.0014 nan 0.0500 0.0001
## 80 0.0007 nan 0.0500 0.0000
## 100 0.0003 nan 0.0500 0.0000
## 120 0.0002 nan 0.0500 0.0000
## 140 0.0001 nan 0.0500 -0.0000
## 160 0.0000 nan 0.0500 0.0000
## 180 0.0000 nan 0.0500 -0.0000
## 200 0.0000 nan 0.0500 0.0000
##
## - Fold08: shrinkage=0.05, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold08: shrinkage=0.05, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0422 nan 0.0500 0.0020
## 2 0.0391 nan 0.0500 0.0023
## 3 0.0366 nan 0.0500 0.0020
## 4 0.0339 nan 0.0500 0.0025
## 5 0.0311 nan 0.0500 0.0011
## 6 0.0299 nan 0.0500 0.0009
## 7 0.0278 nan 0.0500 0.0022
## 8 0.0258 nan 0.0500 0.0009
## 9 0.0237 nan 0.0500 0.0012
## 10 0.0228 nan 0.0500 -0.0002
## 20 0.0116 nan 0.0500 0.0005
## 40 0.0043 nan 0.0500 -0.0001
## 60 0.0019 nan 0.0500 0.0000
## 80 0.0009 nan 0.0500 -0.0000
## 100 0.0005 nan 0.0500 -0.0000
## 120 0.0004 nan 0.0500 0.0000
## 140 0.0002 nan 0.0500 -0.0000
## 160 0.0001 nan 0.0500 0.0000
## 180 0.0001 nan 0.0500 -0.0000
## 200 0.0001 nan 0.0500 -0.0000
##
## - Fold08: shrinkage=0.05, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold08: shrinkage=0.05, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0414 nan 0.0500 0.0025
## 2 0.0383 nan 0.0500 0.0028
## 3 0.0368 nan 0.0500 0.0008
## 4 0.0345 nan 0.0500 0.0019
## 5 0.0329 nan 0.0500 0.0015
## 6 0.0312 nan 0.0500 0.0011
## 7 0.0297 nan 0.0500 0.0018
## 8 0.0280 nan 0.0500 0.0015
## 9 0.0267 nan 0.0500 0.0008
## 10 0.0252 nan 0.0500 0.0008
## 20 0.0159 nan 0.0500 0.0007
## 40 0.0088 nan 0.0500 0.0000
## 60 0.0048 nan 0.0500 0.0002
## 80 0.0029 nan 0.0500 0.0000
## 100 0.0020 nan 0.0500 -0.0000
## 120 0.0013 nan 0.0500 0.0000
## 140 0.0010 nan 0.0500 0.0000
## 160 0.0008 nan 0.0500 -0.0000
## 180 0.0005 nan 0.0500 0.0000
## 200 0.0004 nan 0.0500 -0.0000
##
## - Fold08: shrinkage=0.05, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold08: shrinkage=0.05, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0401 nan 0.0500 0.0027
## 2 0.0366 nan 0.0500 0.0032
## 3 0.0334 nan 0.0500 0.0020
## 4 0.0309 nan 0.0500 0.0019
## 5 0.0292 nan 0.0500 0.0012
## 6 0.0271 nan 0.0500 0.0016
## 7 0.0248 nan 0.0500 0.0010
## 8 0.0230 nan 0.0500 0.0018
## 9 0.0209 nan 0.0500 0.0015
## 10 0.0196 nan 0.0500 0.0009
## 20 0.0098 nan 0.0500 0.0001
## 40 0.0026 nan 0.0500 -0.0001
## 60 0.0009 nan 0.0500 0.0000
## 80 0.0003 nan 0.0500 -0.0000
## 100 0.0001 nan 0.0500 0.0000
## 120 0.0001 nan 0.0500 0.0000
## 140 0.0000 nan 0.0500 -0.0000
## 160 0.0000 nan 0.0500 0.0000
## 180 0.0000 nan 0.0500 0.0000
## 200 0.0000 nan 0.0500 -0.0000
##
## - Fold08: shrinkage=0.05, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold08: shrinkage=0.05, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0415 nan 0.0500 0.0018
## 2 0.0383 nan 0.0500 0.0038
## 3 0.0371 nan 0.0500 0.0012
## 4 0.0348 nan 0.0500 0.0018
## 5 0.0323 nan 0.0500 0.0015
## 6 0.0299 nan 0.0500 0.0013
## 7 0.0274 nan 0.0500 0.0021
## 8 0.0245 nan 0.0500 0.0022
## 9 0.0219 nan 0.0500 0.0017
## 10 0.0207 nan 0.0500 0.0009
## 20 0.0118 nan 0.0500 0.0004
## 40 0.0046 nan 0.0500 0.0001
## 60 0.0020 nan 0.0500 -0.0000
## 80 0.0011 nan 0.0500 0.0000
## 100 0.0006 nan 0.0500 -0.0000
## 120 0.0003 nan 0.0500 0.0000
## 140 0.0002 nan 0.0500 -0.0000
## 160 0.0001 nan 0.0500 0.0000
## 180 0.0001 nan 0.0500 -0.0000
## 200 0.0001 nan 0.0500 -0.0000
##
## - Fold08: shrinkage=0.05, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold08: shrinkage=0.05, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0421 nan 0.0500 0.0018
## 2 0.0399 nan 0.0500 0.0019
## 3 0.0373 nan 0.0500 0.0026
## 4 0.0345 nan 0.0500 0.0025
## 5 0.0326 nan 0.0500 0.0012
## 6 0.0306 nan 0.0500 0.0018
## 7 0.0282 nan 0.0500 0.0018
## 8 0.0273 nan 0.0500 0.0009
## 9 0.0262 nan 0.0500 0.0009
## 10 0.0251 nan 0.0500 0.0009
## 20 0.0159 nan 0.0500 0.0002
## 40 0.0085 nan 0.0500 0.0001
## 60 0.0052 nan 0.0500 -0.0001
## 80 0.0035 nan 0.0500 -0.0001
## 100 0.0025 nan 0.0500 -0.0000
## 120 0.0017 nan 0.0500 0.0000
## 140 0.0012 nan 0.0500 -0.0000
## 160 0.0009 nan 0.0500 -0.0000
## 180 0.0007 nan 0.0500 0.0000
## 200 0.0005 nan 0.0500 -0.0000
##
## - Fold08: shrinkage=0.05, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold08: shrinkage=0.10, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0382 nan 0.1000 0.0062
## 2 0.0330 nan 0.1000 0.0048
## 3 0.0284 nan 0.1000 0.0042
## 4 0.0257 nan 0.1000 0.0030
## 5 0.0233 nan 0.1000 -0.0004
## 6 0.0205 nan 0.1000 0.0024
## 7 0.0188 nan 0.1000 0.0011
## 8 0.0172 nan 0.1000 0.0014
## 9 0.0163 nan 0.1000 0.0011
## 10 0.0137 nan 0.1000 0.0031
## 20 0.0060 nan 0.1000 -0.0004
## 40 0.0019 nan 0.1000 0.0001
## 60 0.0006 nan 0.1000 -0.0000
## 80 0.0003 nan 0.1000 -0.0000
## 100 0.0001 nan 0.1000 0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold08: shrinkage=0.10, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold08: shrinkage=0.10, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0396 nan 0.1000 0.0046
## 2 0.0354 nan 0.1000 0.0040
## 3 0.0307 nan 0.1000 0.0042
## 4 0.0270 nan 0.1000 0.0036
## 5 0.0240 nan 0.1000 0.0010
## 6 0.0219 nan 0.1000 0.0018
## 7 0.0189 nan 0.1000 0.0022
## 8 0.0171 nan 0.1000 0.0005
## 9 0.0151 nan 0.1000 0.0015
## 10 0.0134 nan 0.1000 0.0010
## 20 0.0055 nan 0.1000 0.0003
## 40 0.0017 nan 0.1000 0.0001
## 60 0.0006 nan 0.1000 0.0000
## 80 0.0003 nan 0.1000 -0.0000
## 100 0.0001 nan 0.1000 -0.0000
## 120 0.0001 nan 0.1000 0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold08: shrinkage=0.10, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold08: shrinkage=0.10, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0377 nan 0.1000 0.0061
## 2 0.0338 nan 0.1000 0.0040
## 3 0.0296 nan 0.1000 0.0037
## 4 0.0265 nan 0.1000 0.0012
## 5 0.0228 nan 0.1000 0.0030
## 6 0.0204 nan 0.1000 0.0024
## 7 0.0180 nan 0.1000 0.0011
## 8 0.0162 nan 0.1000 0.0010
## 9 0.0147 nan 0.1000 0.0014
## 10 0.0141 nan 0.1000 0.0006
## 20 0.0076 nan 0.1000 -0.0001
## 40 0.0027 nan 0.1000 -0.0000
## 60 0.0014 nan 0.1000 -0.0000
## 80 0.0007 nan 0.1000 -0.0000
## 100 0.0003 nan 0.1000 0.0000
## 120 0.0002 nan 0.1000 0.0000
## 140 0.0001 nan 0.1000 -0.0000
## 160 0.0001 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold08: shrinkage=0.10, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold08: shrinkage=0.10, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0402 nan 0.1000 0.0032
## 2 0.0345 nan 0.1000 0.0039
## 3 0.0311 nan 0.1000 0.0024
## 4 0.0255 nan 0.1000 0.0042
## 5 0.0234 nan 0.1000 0.0013
## 6 0.0210 nan 0.1000 0.0008
## 7 0.0175 nan 0.1000 0.0034
## 8 0.0154 nan 0.1000 0.0023
## 9 0.0133 nan 0.1000 0.0017
## 10 0.0118 nan 0.1000 0.0007
## 20 0.0046 nan 0.1000 -0.0008
## 40 0.0010 nan 0.1000 0.0000
## 60 0.0002 nan 0.1000 0.0000
## 80 0.0001 nan 0.1000 0.0000
## 100 0.0000 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold08: shrinkage=0.10, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold08: shrinkage=0.10, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0379 nan 0.1000 0.0038
## 2 0.0356 nan 0.1000 -0.0002
## 3 0.0310 nan 0.1000 0.0044
## 4 0.0284 nan 0.1000 0.0013
## 5 0.0259 nan 0.1000 0.0018
## 6 0.0246 nan 0.1000 0.0008
## 7 0.0216 nan 0.1000 0.0023
## 8 0.0185 nan 0.1000 0.0009
## 9 0.0166 nan 0.1000 0.0010
## 10 0.0147 nan 0.1000 0.0014
## 20 0.0048 nan 0.1000 0.0003
## 40 0.0013 nan 0.1000 0.0000
## 60 0.0004 nan 0.1000 -0.0000
## 80 0.0002 nan 0.1000 0.0000
## 100 0.0001 nan 0.1000 -0.0000
## 120 0.0001 nan 0.1000 0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 0.0000
##
## - Fold08: shrinkage=0.10, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold08: shrinkage=0.10, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0381 nan 0.1000 0.0051
## 2 0.0333 nan 0.1000 0.0044
## 3 0.0312 nan 0.1000 0.0009
## 4 0.0282 nan 0.1000 0.0024
## 5 0.0249 nan 0.1000 0.0025
## 6 0.0232 nan 0.1000 0.0013
## 7 0.0202 nan 0.1000 0.0017
## 8 0.0188 nan 0.1000 -0.0007
## 9 0.0171 nan 0.1000 0.0005
## 10 0.0154 nan 0.1000 0.0006
## 20 0.0081 nan 0.1000 -0.0003
## 40 0.0036 nan 0.1000 0.0001
## 60 0.0018 nan 0.1000 -0.0001
## 80 0.0008 nan 0.1000 -0.0000
## 100 0.0004 nan 0.1000 -0.0000
## 120 0.0003 nan 0.1000 -0.0000
## 140 0.0002 nan 0.1000 -0.0000
## 160 0.0001 nan 0.1000 0.0000
## 180 0.0001 nan 0.1000 -0.0000
## 200 0.0001 nan 0.1000 -0.0000
##
## - Fold08: shrinkage=0.10, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold08: shrinkage=0.10, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0387 nan 0.1000 0.0053
## 2 0.0325 nan 0.1000 0.0062
## 3 0.0263 nan 0.1000 0.0029
## 4 0.0228 nan 0.1000 0.0024
## 5 0.0190 nan 0.1000 0.0034
## 6 0.0151 nan 0.1000 0.0022
## 7 0.0132 nan 0.1000 -0.0006
## 8 0.0122 nan 0.1000 -0.0006
## 9 0.0109 nan 0.1000 0.0009
## 10 0.0095 nan 0.1000 0.0004
## 20 0.0036 nan 0.1000 -0.0001
## 40 0.0008 nan 0.1000 -0.0000
## 60 0.0001 nan 0.1000 -0.0000
## 80 0.0000 nan 0.1000 -0.0000
## 100 0.0000 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 0.0000
##
## - Fold08: shrinkage=0.10, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold08: shrinkage=0.10, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0367 nan 0.1000 0.0038
## 2 0.0329 nan 0.1000 0.0016
## 3 0.0285 nan 0.1000 0.0039
## 4 0.0251 nan 0.1000 0.0022
## 5 0.0215 nan 0.1000 0.0009
## 6 0.0178 nan 0.1000 0.0027
## 7 0.0160 nan 0.1000 0.0016
## 8 0.0137 nan 0.1000 0.0016
## 9 0.0121 nan 0.1000 0.0013
## 10 0.0107 nan 0.1000 0.0001
## 20 0.0038 nan 0.1000 0.0003
## 40 0.0009 nan 0.1000 0.0000
## 60 0.0003 nan 0.1000 0.0000
## 80 0.0001 nan 0.1000 0.0000
## 100 0.0001 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold08: shrinkage=0.10, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold08: shrinkage=0.10, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0397 nan 0.1000 0.0025
## 2 0.0353 nan 0.1000 0.0050
## 3 0.0313 nan 0.1000 0.0047
## 4 0.0275 nan 0.1000 0.0019
## 5 0.0242 nan 0.1000 0.0031
## 6 0.0217 nan 0.1000 0.0007
## 7 0.0199 nan 0.1000 0.0020
## 8 0.0180 nan 0.1000 0.0022
## 9 0.0166 nan 0.1000 0.0012
## 10 0.0146 nan 0.1000 0.0010
## 20 0.0071 nan 0.1000 0.0003
## 40 0.0034 nan 0.1000 -0.0000
## 60 0.0015 nan 0.1000 0.0000
## 80 0.0008 nan 0.1000 -0.0000
## 100 0.0004 nan 0.1000 0.0000
## 120 0.0002 nan 0.1000 -0.0000
## 140 0.0002 nan 0.1000 -0.0000
## 160 0.0001 nan 0.1000 -0.0000
## 180 0.0001 nan 0.1000 -0.0000
## 200 0.0001 nan 0.1000 -0.0000
##
## - Fold08: shrinkage=0.10, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold09: shrinkage=0.01, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0403 nan 0.0100 0.0005
## 2 0.0398 nan 0.0100 0.0006
## 3 0.0393 nan 0.0100 0.0005
## 4 0.0388 nan 0.0100 0.0006
## 5 0.0382 nan 0.0100 0.0004
## 6 0.0375 nan 0.0100 0.0006
## 7 0.0371 nan 0.0100 0.0003
## 8 0.0365 nan 0.0100 0.0003
## 9 0.0361 nan 0.0100 0.0003
## 10 0.0359 nan 0.0100 0.0001
## 20 0.0317 nan 0.0100 0.0004
## 40 0.0255 nan 0.0100 0.0003
## 60 0.0204 nan 0.0100 -0.0001
## 80 0.0166 nan 0.0100 0.0001
## 100 0.0135 nan 0.0100 0.0001
## 120 0.0110 nan 0.0100 0.0001
## 140 0.0092 nan 0.0100 0.0001
## 160 0.0075 nan 0.0100 0.0000
## 180 0.0063 nan 0.0100 -0.0000
## 200 0.0053 nan 0.0100 0.0000
##
## - Fold09: shrinkage=0.01, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold09: shrinkage=0.01, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0404 nan 0.0100 0.0001
## 2 0.0400 nan 0.0100 0.0002
## 3 0.0395 nan 0.0100 0.0005
## 4 0.0389 nan 0.0100 0.0004
## 5 0.0384 nan 0.0100 0.0002
## 6 0.0379 nan 0.0100 0.0004
## 7 0.0375 nan 0.0100 0.0003
## 8 0.0371 nan 0.0100 0.0000
## 9 0.0365 nan 0.0100 0.0005
## 10 0.0361 nan 0.0100 0.0004
## 20 0.0323 nan 0.0100 0.0003
## 40 0.0255 nan 0.0100 0.0003
## 60 0.0205 nan 0.0100 0.0002
## 80 0.0165 nan 0.0100 0.0002
## 100 0.0134 nan 0.0100 0.0001
## 120 0.0113 nan 0.0100 0.0000
## 140 0.0094 nan 0.0100 0.0001
## 160 0.0080 nan 0.0100 -0.0000
## 180 0.0067 nan 0.0100 0.0000
## 200 0.0057 nan 0.0100 0.0000
##
## - Fold09: shrinkage=0.01, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold09: shrinkage=0.01, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0403 nan 0.0100 0.0006
## 2 0.0399 nan 0.0100 0.0003
## 3 0.0393 nan 0.0100 0.0004
## 4 0.0387 nan 0.0100 0.0005
## 5 0.0385 nan 0.0100 -0.0000
## 6 0.0380 nan 0.0100 0.0005
## 7 0.0377 nan 0.0100 0.0002
## 8 0.0373 nan 0.0100 0.0005
## 9 0.0368 nan 0.0100 0.0003
## 10 0.0363 nan 0.0100 0.0004
## 20 0.0320 nan 0.0100 0.0003
## 40 0.0254 nan 0.0100 0.0002
## 60 0.0209 nan 0.0100 0.0001
## 80 0.0171 nan 0.0100 0.0002
## 100 0.0140 nan 0.0100 0.0001
## 120 0.0118 nan 0.0100 0.0000
## 140 0.0102 nan 0.0100 0.0001
## 160 0.0089 nan 0.0100 0.0000
## 180 0.0081 nan 0.0100 -0.0000
## 200 0.0071 nan 0.0100 0.0000
##
## - Fold09: shrinkage=0.01, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold09: shrinkage=0.01, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0402 nan 0.0100 0.0005
## 2 0.0395 nan 0.0100 0.0003
## 3 0.0389 nan 0.0100 0.0006
## 4 0.0384 nan 0.0100 0.0004
## 5 0.0378 nan 0.0100 0.0005
## 6 0.0372 nan 0.0100 0.0004
## 7 0.0366 nan 0.0100 0.0005
## 8 0.0362 nan 0.0100 -0.0000
## 9 0.0356 nan 0.0100 0.0003
## 10 0.0349 nan 0.0100 0.0007
## 20 0.0307 nan 0.0100 0.0002
## 40 0.0231 nan 0.0100 0.0003
## 60 0.0179 nan 0.0100 0.0002
## 80 0.0140 nan 0.0100 0.0000
## 100 0.0109 nan 0.0100 0.0000
## 120 0.0088 nan 0.0100 0.0001
## 140 0.0071 nan 0.0100 -0.0000
## 160 0.0059 nan 0.0100 -0.0000
## 180 0.0047 nan 0.0100 0.0000
## 200 0.0038 nan 0.0100 0.0000
##
## - Fold09: shrinkage=0.01, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold09: shrinkage=0.01, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0402 nan 0.0100 0.0006
## 2 0.0397 nan 0.0100 0.0004
## 3 0.0390 nan 0.0100 0.0005
## 4 0.0387 nan 0.0100 0.0000
## 5 0.0382 nan 0.0100 0.0002
## 6 0.0379 nan 0.0100 0.0001
## 7 0.0374 nan 0.0100 0.0005
## 8 0.0368 nan 0.0100 0.0005
## 9 0.0364 nan 0.0100 0.0002
## 10 0.0359 nan 0.0100 0.0004
## 20 0.0307 nan 0.0100 0.0004
## 40 0.0239 nan 0.0100 0.0003
## 60 0.0187 nan 0.0100 0.0002
## 80 0.0146 nan 0.0100 0.0002
## 100 0.0115 nan 0.0100 0.0001
## 120 0.0093 nan 0.0100 0.0001
## 140 0.0073 nan 0.0100 0.0000
## 160 0.0058 nan 0.0100 0.0000
## 180 0.0048 nan 0.0100 0.0000
## 200 0.0039 nan 0.0100 0.0000
##
## - Fold09: shrinkage=0.01, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold09: shrinkage=0.01, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0403 nan 0.0100 0.0004
## 2 0.0398 nan 0.0100 0.0004
## 3 0.0393 nan 0.0100 0.0004
## 4 0.0387 nan 0.0100 0.0004
## 5 0.0383 nan 0.0100 0.0005
## 6 0.0378 nan 0.0100 0.0005
## 7 0.0373 nan 0.0100 0.0005
## 8 0.0369 nan 0.0100 0.0003
## 9 0.0365 nan 0.0100 0.0003
## 10 0.0361 nan 0.0100 0.0003
## 20 0.0324 nan 0.0100 0.0004
## 40 0.0263 nan 0.0100 0.0003
## 60 0.0216 nan 0.0100 0.0000
## 80 0.0175 nan 0.0100 0.0001
## 100 0.0149 nan 0.0100 0.0001
## 120 0.0128 nan 0.0100 -0.0001
## 140 0.0109 nan 0.0100 0.0001
## 160 0.0097 nan 0.0100 0.0000
## 180 0.0086 nan 0.0100 -0.0000
## 200 0.0076 nan 0.0100 0.0000
##
## - Fold09: shrinkage=0.01, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold09: shrinkage=0.01, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0404 nan 0.0100 0.0002
## 2 0.0396 nan 0.0100 0.0003
## 3 0.0393 nan 0.0100 0.0003
## 4 0.0388 nan 0.0100 0.0005
## 5 0.0382 nan 0.0100 0.0005
## 6 0.0376 nan 0.0100 0.0006
## 7 0.0373 nan 0.0100 0.0001
## 8 0.0367 nan 0.0100 0.0005
## 9 0.0361 nan 0.0100 0.0003
## 10 0.0357 nan 0.0100 0.0004
## 20 0.0305 nan 0.0100 0.0005
## 40 0.0226 nan 0.0100 0.0001
## 60 0.0170 nan 0.0100 0.0002
## 80 0.0131 nan 0.0100 0.0001
## 100 0.0099 nan 0.0100 0.0001
## 120 0.0077 nan 0.0100 0.0001
## 140 0.0060 nan 0.0100 0.0000
## 160 0.0047 nan 0.0100 0.0000
## 180 0.0037 nan 0.0100 0.0000
## 200 0.0030 nan 0.0100 0.0000
##
## - Fold09: shrinkage=0.01, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold09: shrinkage=0.01, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0402 nan 0.0100 0.0004
## 2 0.0396 nan 0.0100 0.0006
## 3 0.0389 nan 0.0100 0.0004
## 4 0.0383 nan 0.0100 0.0001
## 5 0.0379 nan 0.0100 0.0001
## 6 0.0375 nan 0.0100 0.0003
## 7 0.0370 nan 0.0100 0.0003
## 8 0.0365 nan 0.0100 0.0006
## 9 0.0360 nan 0.0100 0.0005
## 10 0.0355 nan 0.0100 0.0003
## 20 0.0310 nan 0.0100 0.0004
## 40 0.0239 nan 0.0100 0.0002
## 60 0.0182 nan 0.0100 0.0002
## 80 0.0137 nan 0.0100 0.0001
## 100 0.0109 nan 0.0100 0.0000
## 120 0.0088 nan 0.0100 0.0000
## 140 0.0070 nan 0.0100 0.0000
## 160 0.0056 nan 0.0100 0.0000
## 180 0.0046 nan 0.0100 -0.0000
## 200 0.0038 nan 0.0100 -0.0000
##
## - Fold09: shrinkage=0.01, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold09: shrinkage=0.01, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0403 nan 0.0100 0.0006
## 2 0.0399 nan 0.0100 0.0004
## 3 0.0392 nan 0.0100 0.0004
## 4 0.0389 nan 0.0100 0.0003
## 5 0.0385 nan 0.0100 0.0004
## 6 0.0379 nan 0.0100 0.0002
## 7 0.0375 nan 0.0100 0.0003
## 8 0.0371 nan 0.0100 0.0003
## 9 0.0367 nan 0.0100 0.0005
## 10 0.0363 nan 0.0100 0.0004
## 20 0.0322 nan 0.0100 0.0004
## 40 0.0257 nan 0.0100 0.0002
## 60 0.0212 nan 0.0100 0.0002
## 80 0.0175 nan 0.0100 0.0000
## 100 0.0147 nan 0.0100 0.0001
## 120 0.0124 nan 0.0100 0.0001
## 140 0.0106 nan 0.0100 0.0001
## 160 0.0092 nan 0.0100 0.0000
## 180 0.0081 nan 0.0100 0.0000
## 200 0.0071 nan 0.0100 0.0000
##
## - Fold09: shrinkage=0.01, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold09: shrinkage=0.05, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0385 nan 0.0500 0.0025
## 2 0.0375 nan 0.0500 -0.0009
## 3 0.0354 nan 0.0500 0.0023
## 4 0.0347 nan 0.0500 -0.0001
## 5 0.0328 nan 0.0500 0.0002
## 6 0.0317 nan 0.0500 0.0010
## 7 0.0294 nan 0.0500 0.0021
## 8 0.0280 nan 0.0500 0.0017
## 9 0.0266 nan 0.0500 0.0012
## 10 0.0257 nan 0.0500 0.0006
## 20 0.0156 nan 0.0500 0.0005
## 40 0.0072 nan 0.0500 -0.0005
## 60 0.0037 nan 0.0500 -0.0000
## 80 0.0021 nan 0.0500 0.0000
## 100 0.0013 nan 0.0500 0.0000
## 120 0.0008 nan 0.0500 -0.0000
## 140 0.0005 nan 0.0500 -0.0000
## 160 0.0003 nan 0.0500 -0.0000
## 180 0.0002 nan 0.0500 -0.0000
## 200 0.0001 nan 0.0500 -0.0000
##
## - Fold09: shrinkage=0.05, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold09: shrinkage=0.05, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0378 nan 0.0500 0.0023
## 2 0.0348 nan 0.0500 0.0024
## 3 0.0320 nan 0.0500 0.0020
## 4 0.0298 nan 0.0500 0.0013
## 5 0.0280 nan 0.0500 0.0016
## 6 0.0262 nan 0.0500 0.0007
## 7 0.0250 nan 0.0500 0.0001
## 8 0.0233 nan 0.0500 0.0013
## 9 0.0219 nan 0.0500 0.0014
## 10 0.0207 nan 0.0500 0.0004
## 20 0.0135 nan 0.0500 0.0003
## 40 0.0050 nan 0.0500 0.0002
## 60 0.0023 nan 0.0500 0.0000
## 80 0.0013 nan 0.0500 -0.0000
## 100 0.0007 nan 0.0500 -0.0000
## 120 0.0004 nan 0.0500 -0.0000
## 140 0.0003 nan 0.0500 -0.0000
## 160 0.0002 nan 0.0500 -0.0000
## 180 0.0001 nan 0.0500 0.0000
## 200 0.0001 nan 0.0500 -0.0000
##
## - Fold09: shrinkage=0.05, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold09: shrinkage=0.05, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0380 nan 0.0500 0.0027
## 2 0.0359 nan 0.0500 0.0011
## 3 0.0333 nan 0.0500 0.0016
## 4 0.0315 nan 0.0500 0.0015
## 5 0.0296 nan 0.0500 0.0011
## 6 0.0284 nan 0.0500 0.0008
## 7 0.0270 nan 0.0500 0.0010
## 8 0.0257 nan 0.0500 0.0013
## 9 0.0247 nan 0.0500 0.0007
## 10 0.0241 nan 0.0500 0.0001
## 20 0.0156 nan 0.0500 0.0002
## 40 0.0085 nan 0.0500 0.0001
## 60 0.0051 nan 0.0500 0.0000
## 80 0.0036 nan 0.0500 -0.0000
## 100 0.0023 nan 0.0500 -0.0000
## 120 0.0017 nan 0.0500 0.0000
## 140 0.0012 nan 0.0500 -0.0000
## 160 0.0010 nan 0.0500 -0.0000
## 180 0.0007 nan 0.0500 0.0000
## 200 0.0005 nan 0.0500 0.0000
##
## - Fold09: shrinkage=0.05, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold09: shrinkage=0.05, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0384 nan 0.0500 0.0013
## 2 0.0367 nan 0.0500 0.0006
## 3 0.0345 nan 0.0500 0.0016
## 4 0.0319 nan 0.0500 0.0015
## 5 0.0293 nan 0.0500 0.0006
## 6 0.0269 nan 0.0500 0.0020
## 7 0.0249 nan 0.0500 0.0008
## 8 0.0233 nan 0.0500 0.0007
## 9 0.0215 nan 0.0500 0.0014
## 10 0.0198 nan 0.0500 0.0018
## 20 0.0102 nan 0.0500 0.0003
## 40 0.0029 nan 0.0500 0.0001
## 60 0.0012 nan 0.0500 0.0000
## 80 0.0006 nan 0.0500 -0.0000
## 100 0.0003 nan 0.0500 0.0000
## 120 0.0002 nan 0.0500 -0.0000
## 140 0.0001 nan 0.0500 -0.0000
## 160 0.0000 nan 0.0500 -0.0000
## 180 0.0000 nan 0.0500 -0.0000
## 200 0.0000 nan 0.0500 -0.0000
##
## - Fold09: shrinkage=0.05, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold09: shrinkage=0.05, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0383 nan 0.0500 0.0021
## 2 0.0362 nan 0.0500 0.0026
## 3 0.0333 nan 0.0500 0.0023
## 4 0.0308 nan 0.0500 0.0018
## 5 0.0289 nan 0.0500 0.0021
## 6 0.0274 nan 0.0500 0.0014
## 7 0.0254 nan 0.0500 0.0003
## 8 0.0230 nan 0.0500 0.0017
## 9 0.0213 nan 0.0500 0.0014
## 10 0.0194 nan 0.0500 0.0006
## 20 0.0102 nan 0.0500 0.0002
## 40 0.0040 nan 0.0500 0.0002
## 60 0.0021 nan 0.0500 0.0001
## 80 0.0012 nan 0.0500 -0.0000
## 100 0.0006 nan 0.0500 -0.0000
## 120 0.0004 nan 0.0500 -0.0000
## 140 0.0003 nan 0.0500 0.0000
## 160 0.0002 nan 0.0500 -0.0000
## 180 0.0001 nan 0.0500 0.0000
## 200 0.0001 nan 0.0500 -0.0000
##
## - Fold09: shrinkage=0.05, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold09: shrinkage=0.05, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0380 nan 0.0500 0.0025
## 2 0.0360 nan 0.0500 0.0019
## 3 0.0338 nan 0.0500 0.0021
## 4 0.0317 nan 0.0500 0.0021
## 5 0.0297 nan 0.0500 0.0018
## 6 0.0284 nan 0.0500 0.0013
## 7 0.0265 nan 0.0500 0.0017
## 8 0.0251 nan 0.0500 0.0007
## 9 0.0243 nan 0.0500 0.0007
## 10 0.0235 nan 0.0500 0.0009
## 20 0.0149 nan 0.0500 0.0007
## 40 0.0074 nan 0.0500 0.0001
## 60 0.0044 nan 0.0500 -0.0000
## 80 0.0031 nan 0.0500 0.0000
## 100 0.0021 nan 0.0500 0.0000
## 120 0.0014 nan 0.0500 0.0000
## 140 0.0010 nan 0.0500 0.0000
## 160 0.0008 nan 0.0500 -0.0000
## 180 0.0006 nan 0.0500 -0.0000
## 200 0.0004 nan 0.0500 -0.0000
##
## - Fold09: shrinkage=0.05, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold09: shrinkage=0.05, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0393 nan 0.0500 -0.0001
## 2 0.0380 nan 0.0500 -0.0002
## 3 0.0347 nan 0.0500 0.0033
## 4 0.0314 nan 0.0500 0.0022
## 5 0.0287 nan 0.0500 0.0030
## 6 0.0269 nan 0.0500 0.0013
## 7 0.0259 nan 0.0500 0.0008
## 8 0.0249 nan 0.0500 0.0005
## 9 0.0232 nan 0.0500 0.0002
## 10 0.0219 nan 0.0500 0.0007
## 20 0.0116 nan 0.0500 0.0003
## 40 0.0034 nan 0.0500 0.0000
## 60 0.0012 nan 0.0500 -0.0000
## 80 0.0006 nan 0.0500 -0.0000
## 100 0.0002 nan 0.0500 0.0000
## 120 0.0001 nan 0.0500 -0.0000
## 140 0.0001 nan 0.0500 -0.0000
## 160 0.0000 nan 0.0500 -0.0000
## 180 0.0000 nan 0.0500 0.0000
## 200 0.0000 nan 0.0500 -0.0000
##
## - Fold09: shrinkage=0.05, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold09: shrinkage=0.05, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0384 nan 0.0500 0.0012
## 2 0.0355 nan 0.0500 0.0033
## 3 0.0331 nan 0.0500 0.0018
## 4 0.0317 nan 0.0500 0.0010
## 5 0.0295 nan 0.0500 0.0020
## 6 0.0289 nan 0.0500 0.0001
## 7 0.0264 nan 0.0500 0.0014
## 8 0.0249 nan 0.0500 0.0010
## 9 0.0236 nan 0.0500 0.0010
## 10 0.0219 nan 0.0500 0.0017
## 20 0.0116 nan 0.0500 0.0005
## 40 0.0045 nan 0.0500 0.0001
## 60 0.0019 nan 0.0500 0.0000
## 80 0.0010 nan 0.0500 -0.0000
## 100 0.0006 nan 0.0500 -0.0000
## 120 0.0003 nan 0.0500 -0.0000
## 140 0.0002 nan 0.0500 -0.0000
## 160 0.0002 nan 0.0500 -0.0000
## 180 0.0001 nan 0.0500 -0.0000
## 200 0.0001 nan 0.0500 0.0000
##
## - Fold09: shrinkage=0.05, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold09: shrinkage=0.05, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0389 nan 0.0500 0.0010
## 2 0.0361 nan 0.0500 0.0026
## 3 0.0341 nan 0.0500 0.0023
## 4 0.0326 nan 0.0500 0.0012
## 5 0.0311 nan 0.0500 0.0010
## 6 0.0289 nan 0.0500 0.0020
## 7 0.0273 nan 0.0500 0.0014
## 8 0.0258 nan 0.0500 0.0015
## 9 0.0244 nan 0.0500 0.0013
## 10 0.0231 nan 0.0500 0.0012
## 20 0.0133 nan 0.0500 0.0005
## 40 0.0059 nan 0.0500 0.0001
## 60 0.0036 nan 0.0500 0.0000
## 80 0.0023 nan 0.0500 -0.0000
## 100 0.0015 nan 0.0500 -0.0000
## 120 0.0011 nan 0.0500 -0.0000
## 140 0.0008 nan 0.0500 0.0000
## 160 0.0005 nan 0.0500 -0.0000
## 180 0.0004 nan 0.0500 -0.0000
## 200 0.0003 nan 0.0500 0.0000
##
## - Fold09: shrinkage=0.05, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold09: shrinkage=0.10, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0374 nan 0.1000 0.0016
## 2 0.0320 nan 0.1000 0.0046
## 3 0.0280 nan 0.1000 0.0037
## 4 0.0240 nan 0.1000 0.0010
## 5 0.0212 nan 0.1000 0.0014
## 6 0.0192 nan 0.1000 0.0016
## 7 0.0176 nan 0.1000 0.0017
## 8 0.0156 nan 0.1000 0.0016
## 9 0.0143 nan 0.1000 0.0014
## 10 0.0127 nan 0.1000 0.0015
## 20 0.0059 nan 0.1000 0.0002
## 40 0.0018 nan 0.1000 -0.0001
## 60 0.0006 nan 0.1000 -0.0000
## 80 0.0003 nan 0.1000 -0.0000
## 100 0.0001 nan 0.1000 0.0000
## 120 0.0001 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold09: shrinkage=0.10, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold09: shrinkage=0.10, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0358 nan 0.1000 0.0058
## 2 0.0316 nan 0.1000 0.0034
## 3 0.0285 nan 0.1000 0.0026
## 4 0.0267 nan 0.1000 0.0005
## 5 0.0246 nan 0.1000 0.0006
## 6 0.0227 nan 0.1000 0.0002
## 7 0.0201 nan 0.1000 0.0018
## 8 0.0184 nan 0.1000 0.0012
## 9 0.0158 nan 0.1000 0.0016
## 10 0.0147 nan 0.1000 0.0008
## 20 0.0063 nan 0.1000 0.0002
## 40 0.0022 nan 0.1000 0.0001
## 60 0.0010 nan 0.1000 -0.0001
## 80 0.0004 nan 0.1000 0.0000
## 100 0.0002 nan 0.1000 -0.0000
## 120 0.0001 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 0.0000
##
## - Fold09: shrinkage=0.10, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold09: shrinkage=0.10, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0360 nan 0.1000 0.0045
## 2 0.0329 nan 0.1000 0.0039
## 3 0.0302 nan 0.1000 0.0007
## 4 0.0266 nan 0.1000 0.0034
## 5 0.0247 nan 0.1000 -0.0008
## 6 0.0220 nan 0.1000 0.0025
## 7 0.0201 nan 0.1000 0.0004
## 8 0.0189 nan 0.1000 0.0009
## 9 0.0175 nan 0.1000 0.0016
## 10 0.0162 nan 0.1000 0.0008
## 20 0.0072 nan 0.1000 0.0006
## 40 0.0033 nan 0.1000 0.0000
## 60 0.0019 nan 0.1000 -0.0000
## 80 0.0011 nan 0.1000 -0.0001
## 100 0.0007 nan 0.1000 -0.0000
## 120 0.0004 nan 0.1000 -0.0000
## 140 0.0002 nan 0.1000 -0.0000
## 160 0.0001 nan 0.1000 -0.0000
## 180 0.0001 nan 0.1000 -0.0000
## 200 0.0001 nan 0.1000 0.0000
##
## - Fold09: shrinkage=0.10, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold09: shrinkage=0.10, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0372 nan 0.1000 0.0039
## 2 0.0347 nan 0.1000 0.0005
## 3 0.0295 nan 0.1000 0.0042
## 4 0.0249 nan 0.1000 0.0035
## 5 0.0225 nan 0.1000 0.0023
## 6 0.0197 nan 0.1000 0.0018
## 7 0.0183 nan 0.1000 0.0013
## 8 0.0156 nan 0.1000 0.0026
## 9 0.0134 nan 0.1000 0.0010
## 10 0.0121 nan 0.1000 0.0001
## 20 0.0033 nan 0.1000 0.0004
## 40 0.0007 nan 0.1000 0.0000
## 60 0.0002 nan 0.1000 -0.0000
## 80 0.0001 nan 0.1000 -0.0000
## 100 0.0000 nan 0.1000 0.0000
## 120 0.0000 nan 0.1000 0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold09: shrinkage=0.10, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold09: shrinkage=0.10, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0337 nan 0.1000 0.0060
## 2 0.0285 nan 0.1000 0.0030
## 3 0.0238 nan 0.1000 0.0042
## 4 0.0210 nan 0.1000 0.0006
## 5 0.0193 nan 0.1000 -0.0002
## 6 0.0165 nan 0.1000 0.0023
## 7 0.0152 nan 0.1000 0.0002
## 8 0.0140 nan 0.1000 0.0012
## 9 0.0128 nan 0.1000 0.0002
## 10 0.0117 nan 0.1000 0.0014
## 20 0.0036 nan 0.1000 0.0004
## 40 0.0008 nan 0.1000 0.0000
## 60 0.0003 nan 0.1000 0.0000
## 80 0.0001 nan 0.1000 -0.0000
## 100 0.0000 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold09: shrinkage=0.10, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold09: shrinkage=0.10, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0349 nan 0.1000 0.0056
## 2 0.0309 nan 0.1000 0.0012
## 3 0.0282 nan 0.1000 -0.0003
## 4 0.0255 nan 0.1000 0.0016
## 5 0.0233 nan 0.1000 0.0005
## 6 0.0217 nan 0.1000 0.0006
## 7 0.0207 nan 0.1000 0.0000
## 8 0.0179 nan 0.1000 0.0007
## 9 0.0166 nan 0.1000 0.0004
## 10 0.0147 nan 0.1000 0.0009
## 20 0.0077 nan 0.1000 -0.0000
## 40 0.0037 nan 0.1000 -0.0003
## 60 0.0019 nan 0.1000 0.0001
## 80 0.0010 nan 0.1000 -0.0000
## 100 0.0006 nan 0.1000 0.0000
## 120 0.0004 nan 0.1000 -0.0000
## 140 0.0003 nan 0.1000 -0.0000
## 160 0.0002 nan 0.1000 0.0000
## 180 0.0001 nan 0.1000 0.0000
## 200 0.0001 nan 0.1000 -0.0000
##
## - Fold09: shrinkage=0.10, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold09: shrinkage=0.10, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0342 nan 0.1000 0.0034
## 2 0.0298 nan 0.1000 0.0001
## 3 0.0267 nan 0.1000 0.0020
## 4 0.0222 nan 0.1000 0.0033
## 5 0.0200 nan 0.1000 0.0011
## 6 0.0170 nan 0.1000 0.0022
## 7 0.0162 nan 0.1000 -0.0002
## 8 0.0138 nan 0.1000 0.0023
## 9 0.0116 nan 0.1000 0.0010
## 10 0.0098 nan 0.1000 0.0014
## 20 0.0030 nan 0.1000 0.0001
## 40 0.0005 nan 0.1000 -0.0000
## 60 0.0001 nan 0.1000 -0.0000
## 80 0.0000 nan 0.1000 -0.0000
## 100 0.0000 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 0.0000
##
## - Fold09: shrinkage=0.10, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold09: shrinkage=0.10, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0351 nan 0.1000 0.0041
## 2 0.0301 nan 0.1000 0.0048
## 3 0.0271 nan 0.1000 0.0022
## 4 0.0246 nan 0.1000 0.0015
## 5 0.0209 nan 0.1000 0.0023
## 6 0.0183 nan 0.1000 -0.0003
## 7 0.0161 nan 0.1000 0.0020
## 8 0.0140 nan 0.1000 0.0008
## 9 0.0122 nan 0.1000 0.0015
## 10 0.0108 nan 0.1000 0.0005
## 20 0.0042 nan 0.1000 0.0004
## 40 0.0008 nan 0.1000 -0.0000
## 60 0.0003 nan 0.1000 -0.0000
## 80 0.0001 nan 0.1000 -0.0000
## 100 0.0000 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold09: shrinkage=0.10, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold09: shrinkage=0.10, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0357 nan 0.1000 0.0048
## 2 0.0317 nan 0.1000 0.0025
## 3 0.0271 nan 0.1000 0.0030
## 4 0.0232 nan 0.1000 0.0029
## 5 0.0200 nan 0.1000 0.0024
## 6 0.0184 nan 0.1000 0.0010
## 7 0.0168 nan 0.1000 0.0012
## 8 0.0157 nan 0.1000 0.0010
## 9 0.0140 nan 0.1000 0.0011
## 10 0.0131 nan 0.1000 0.0009
## 20 0.0069 nan 0.1000 0.0003
## 40 0.0026 nan 0.1000 0.0001
## 60 0.0013 nan 0.1000 -0.0000
## 80 0.0006 nan 0.1000 -0.0001
## 100 0.0003 nan 0.1000 -0.0000
## 120 0.0002 nan 0.1000 -0.0000
## 140 0.0001 nan 0.1000 -0.0000
## 160 0.0001 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold09: shrinkage=0.10, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold10: shrinkage=0.01, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0434 nan 0.0100 0.0005
## 2 0.0431 nan 0.0100 0.0002
## 3 0.0425 nan 0.0100 0.0005
## 4 0.0420 nan 0.0100 0.0004
## 5 0.0416 nan 0.0100 0.0003
## 6 0.0411 nan 0.0100 0.0005
## 7 0.0406 nan 0.0100 0.0005
## 8 0.0403 nan 0.0100 0.0002
## 9 0.0397 nan 0.0100 0.0005
## 10 0.0393 nan 0.0100 0.0003
## 20 0.0349 nan 0.0100 0.0001
## 40 0.0276 nan 0.0100 0.0004
## 60 0.0221 nan 0.0100 0.0002
## 80 0.0180 nan 0.0100 0.0001
## 100 0.0150 nan 0.0100 0.0002
## 120 0.0126 nan 0.0100 0.0001
## 140 0.0106 nan 0.0100 0.0001
## 160 0.0092 nan 0.0100 0.0001
## 180 0.0077 nan 0.0100 0.0001
## 200 0.0064 nan 0.0100 0.0000
##
## - Fold10: shrinkage=0.01, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold10: shrinkage=0.01, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0436 nan 0.0100 0.0001
## 2 0.0431 nan 0.0100 0.0002
## 3 0.0427 nan 0.0100 0.0005
## 4 0.0422 nan 0.0100 0.0004
## 5 0.0415 nan 0.0100 0.0006
## 6 0.0411 nan 0.0100 0.0005
## 7 0.0406 nan 0.0100 0.0005
## 8 0.0400 nan 0.0100 0.0005
## 9 0.0394 nan 0.0100 0.0004
## 10 0.0390 nan 0.0100 0.0005
## 20 0.0346 nan 0.0100 0.0004
## 40 0.0270 nan 0.0100 0.0003
## 60 0.0219 nan 0.0100 0.0000
## 80 0.0182 nan 0.0100 0.0001
## 100 0.0151 nan 0.0100 0.0001
## 120 0.0124 nan 0.0100 0.0000
## 140 0.0102 nan 0.0100 0.0001
## 160 0.0086 nan 0.0100 0.0000
## 180 0.0075 nan 0.0100 -0.0000
## 200 0.0065 nan 0.0100 -0.0000
##
## - Fold10: shrinkage=0.01, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold10: shrinkage=0.01, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0436 nan 0.0100 0.0004
## 2 0.0432 nan 0.0100 0.0005
## 3 0.0424 nan 0.0100 0.0005
## 4 0.0417 nan 0.0100 0.0006
## 5 0.0413 nan 0.0100 0.0005
## 6 0.0408 nan 0.0100 0.0005
## 7 0.0404 nan 0.0100 0.0005
## 8 0.0400 nan 0.0100 0.0003
## 9 0.0395 nan 0.0100 0.0006
## 10 0.0391 nan 0.0100 0.0002
## 20 0.0346 nan 0.0100 0.0004
## 40 0.0283 nan 0.0100 0.0003
## 60 0.0230 nan 0.0100 0.0002
## 80 0.0191 nan 0.0100 0.0000
## 100 0.0157 nan 0.0100 0.0001
## 120 0.0133 nan 0.0100 0.0001
## 140 0.0113 nan 0.0100 0.0000
## 160 0.0100 nan 0.0100 0.0000
## 180 0.0088 nan 0.0100 -0.0000
## 200 0.0079 nan 0.0100 0.0000
##
## - Fold10: shrinkage=0.01, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold10: shrinkage=0.01, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0435 nan 0.0100 0.0004
## 2 0.0429 nan 0.0100 0.0007
## 3 0.0422 nan 0.0100 0.0004
## 4 0.0414 nan 0.0100 0.0004
## 5 0.0410 nan 0.0100 0.0003
## 6 0.0403 nan 0.0100 0.0003
## 7 0.0396 nan 0.0100 0.0004
## 8 0.0390 nan 0.0100 0.0007
## 9 0.0383 nan 0.0100 0.0005
## 10 0.0376 nan 0.0100 0.0005
## 20 0.0329 nan 0.0100 0.0004
## 40 0.0248 nan 0.0100 0.0004
## 60 0.0188 nan 0.0100 0.0002
## 80 0.0144 nan 0.0100 0.0001
## 100 0.0112 nan 0.0100 0.0000
## 120 0.0088 nan 0.0100 0.0001
## 140 0.0070 nan 0.0100 0.0001
## 160 0.0058 nan 0.0100 0.0000
## 180 0.0047 nan 0.0100 0.0000
## 200 0.0038 nan 0.0100 0.0000
##
## - Fold10: shrinkage=0.01, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold10: shrinkage=0.01, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0433 nan 0.0100 0.0006
## 2 0.0428 nan 0.0100 0.0003
## 3 0.0425 nan 0.0100 0.0002
## 4 0.0418 nan 0.0100 0.0007
## 5 0.0413 nan 0.0100 0.0001
## 6 0.0408 nan 0.0100 0.0005
## 7 0.0403 nan 0.0100 0.0003
## 8 0.0396 nan 0.0100 0.0004
## 9 0.0389 nan 0.0100 0.0005
## 10 0.0384 nan 0.0100 0.0004
## 20 0.0335 nan 0.0100 0.0005
## 40 0.0254 nan 0.0100 0.0002
## 60 0.0196 nan 0.0100 0.0001
## 80 0.0151 nan 0.0100 0.0001
## 100 0.0119 nan 0.0100 0.0001
## 120 0.0097 nan 0.0100 0.0000
## 140 0.0079 nan 0.0100 0.0000
## 160 0.0064 nan 0.0100 0.0000
## 180 0.0052 nan 0.0100 -0.0000
## 200 0.0044 nan 0.0100 0.0000
##
## - Fold10: shrinkage=0.01, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold10: shrinkage=0.01, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0433 nan 0.0100 0.0004
## 2 0.0427 nan 0.0100 0.0006
## 3 0.0422 nan 0.0100 0.0006
## 4 0.0417 nan 0.0100 0.0005
## 5 0.0411 nan 0.0100 0.0005
## 6 0.0406 nan 0.0100 0.0001
## 7 0.0402 nan 0.0100 0.0005
## 8 0.0397 nan 0.0100 0.0005
## 9 0.0392 nan 0.0100 0.0002
## 10 0.0387 nan 0.0100 0.0005
## 20 0.0348 nan 0.0100 0.0005
## 40 0.0282 nan 0.0100 0.0003
## 60 0.0230 nan 0.0100 0.0000
## 80 0.0186 nan 0.0100 0.0001
## 100 0.0156 nan 0.0100 0.0000
## 120 0.0130 nan 0.0100 0.0001
## 140 0.0111 nan 0.0100 0.0001
## 160 0.0098 nan 0.0100 -0.0000
## 180 0.0085 nan 0.0100 0.0000
## 200 0.0078 nan 0.0100 0.0000
##
## - Fold10: shrinkage=0.01, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold10: shrinkage=0.01, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0434 nan 0.0100 0.0004
## 2 0.0427 nan 0.0100 0.0005
## 3 0.0420 nan 0.0100 0.0004
## 4 0.0413 nan 0.0100 0.0006
## 5 0.0407 nan 0.0100 0.0004
## 6 0.0401 nan 0.0100 0.0005
## 7 0.0393 nan 0.0100 0.0008
## 8 0.0386 nan 0.0100 0.0007
## 9 0.0381 nan 0.0100 0.0005
## 10 0.0376 nan 0.0100 0.0006
## 20 0.0329 nan 0.0100 0.0004
## 40 0.0248 nan 0.0100 0.0004
## 60 0.0185 nan 0.0100 0.0002
## 80 0.0143 nan 0.0100 0.0001
## 100 0.0113 nan 0.0100 0.0001
## 120 0.0088 nan 0.0100 0.0001
## 140 0.0071 nan 0.0100 -0.0000
## 160 0.0057 nan 0.0100 0.0000
## 180 0.0047 nan 0.0100 0.0000
## 200 0.0037 nan 0.0100 0.0000
##
## - Fold10: shrinkage=0.01, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold10: shrinkage=0.01, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0434 nan 0.0100 0.0005
## 2 0.0428 nan 0.0100 0.0005
## 3 0.0422 nan 0.0100 0.0004
## 4 0.0417 nan 0.0100 0.0005
## 5 0.0410 nan 0.0100 0.0007
## 6 0.0403 nan 0.0100 0.0006
## 7 0.0397 nan 0.0100 0.0006
## 8 0.0392 nan 0.0100 0.0004
## 9 0.0385 nan 0.0100 0.0004
## 10 0.0379 nan 0.0100 0.0001
## 20 0.0334 nan 0.0100 0.0002
## 40 0.0260 nan 0.0100 0.0001
## 60 0.0204 nan 0.0100 0.0000
## 80 0.0154 nan 0.0100 0.0002
## 100 0.0120 nan 0.0100 -0.0000
## 120 0.0096 nan 0.0100 0.0000
## 140 0.0076 nan 0.0100 0.0000
## 160 0.0061 nan 0.0100 0.0001
## 180 0.0050 nan 0.0100 0.0000
## 200 0.0040 nan 0.0100 0.0000
##
## - Fold10: shrinkage=0.01, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold10: shrinkage=0.01, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0435 nan 0.0100 0.0000
## 2 0.0428 nan 0.0100 0.0006
## 3 0.0423 nan 0.0100 0.0005
## 4 0.0417 nan 0.0100 0.0005
## 5 0.0411 nan 0.0100 0.0006
## 6 0.0406 nan 0.0100 0.0005
## 7 0.0402 nan 0.0100 0.0004
## 8 0.0398 nan 0.0100 0.0003
## 9 0.0392 nan 0.0100 0.0005
## 10 0.0387 nan 0.0100 0.0005
## 20 0.0345 nan 0.0100 0.0004
## 40 0.0275 nan 0.0100 0.0002
## 60 0.0223 nan 0.0100 0.0001
## 80 0.0188 nan 0.0100 0.0002
## 100 0.0155 nan 0.0100 0.0001
## 120 0.0133 nan 0.0100 -0.0000
## 140 0.0114 nan 0.0100 0.0001
## 160 0.0101 nan 0.0100 0.0001
## 180 0.0088 nan 0.0100 0.0000
## 200 0.0079 nan 0.0100 0.0000
##
## - Fold10: shrinkage=0.01, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold10: shrinkage=0.05, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0420 nan 0.0500 -0.0002
## 2 0.0396 nan 0.0500 0.0008
## 3 0.0370 nan 0.0500 0.0018
## 4 0.0355 nan 0.0500 0.0008
## 5 0.0341 nan 0.0500 0.0008
## 6 0.0316 nan 0.0500 0.0016
## 7 0.0296 nan 0.0500 0.0013
## 8 0.0281 nan 0.0500 0.0014
## 9 0.0268 nan 0.0500 0.0010
## 10 0.0253 nan 0.0500 0.0010
## 20 0.0141 nan 0.0500 0.0010
## 40 0.0058 nan 0.0500 0.0000
## 60 0.0030 nan 0.0500 0.0001
## 80 0.0017 nan 0.0500 0.0000
## 100 0.0010 nan 0.0500 -0.0001
## 120 0.0006 nan 0.0500 0.0000
## 140 0.0004 nan 0.0500 0.0000
## 160 0.0002 nan 0.0500 -0.0000
## 180 0.0002 nan 0.0500 0.0000
## 200 0.0001 nan 0.0500 -0.0000
##
## - Fold10: shrinkage=0.05, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold10: shrinkage=0.05, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0425 nan 0.0500 -0.0006
## 2 0.0399 nan 0.0500 0.0026
## 3 0.0370 nan 0.0500 0.0012
## 4 0.0352 nan 0.0500 0.0016
## 5 0.0340 nan 0.0500 0.0003
## 6 0.0318 nan 0.0500 0.0021
## 7 0.0298 nan 0.0500 0.0017
## 8 0.0289 nan 0.0500 0.0011
## 9 0.0274 nan 0.0500 0.0008
## 10 0.0266 nan 0.0500 0.0008
## 20 0.0173 nan 0.0500 0.0008
## 40 0.0066 nan 0.0500 0.0000
## 60 0.0033 nan 0.0500 -0.0001
## 80 0.0018 nan 0.0500 -0.0000
## 100 0.0010 nan 0.0500 0.0000
## 120 0.0006 nan 0.0500 -0.0000
## 140 0.0004 nan 0.0500 0.0000
## 160 0.0002 nan 0.0500 0.0000
## 180 0.0002 nan 0.0500 -0.0000
## 200 0.0001 nan 0.0500 -0.0000
##
## - Fold10: shrinkage=0.05, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold10: shrinkage=0.05, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0430 nan 0.0500 -0.0000
## 2 0.0402 nan 0.0500 0.0016
## 3 0.0376 nan 0.0500 0.0024
## 4 0.0355 nan 0.0500 0.0021
## 5 0.0332 nan 0.0500 0.0019
## 6 0.0314 nan 0.0500 0.0011
## 7 0.0295 nan 0.0500 0.0008
## 8 0.0282 nan 0.0500 0.0011
## 9 0.0267 nan 0.0500 0.0014
## 10 0.0248 nan 0.0500 0.0015
## 20 0.0156 nan 0.0500 0.0003
## 40 0.0080 nan 0.0500 0.0001
## 60 0.0046 nan 0.0500 -0.0000
## 80 0.0028 nan 0.0500 0.0001
## 100 0.0019 nan 0.0500 -0.0000
## 120 0.0014 nan 0.0500 0.0000
## 140 0.0009 nan 0.0500 -0.0000
## 160 0.0006 nan 0.0500 -0.0000
## 180 0.0005 nan 0.0500 0.0000
## 200 0.0004 nan 0.0500 0.0000
##
## - Fold10: shrinkage=0.05, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold10: shrinkage=0.05, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0409 nan 0.0500 0.0033
## 2 0.0372 nan 0.0500 0.0030
## 3 0.0347 nan 0.0500 0.0017
## 4 0.0319 nan 0.0500 0.0029
## 5 0.0305 nan 0.0500 0.0005
## 6 0.0283 nan 0.0500 0.0016
## 7 0.0260 nan 0.0500 0.0016
## 8 0.0246 nan 0.0500 0.0000
## 9 0.0231 nan 0.0500 0.0011
## 10 0.0215 nan 0.0500 0.0010
## 20 0.0115 nan 0.0500 0.0003
## 40 0.0039 nan 0.0500 0.0001
## 60 0.0015 nan 0.0500 0.0000
## 80 0.0007 nan 0.0500 -0.0000
## 100 0.0004 nan 0.0500 0.0000
## 120 0.0002 nan 0.0500 0.0000
## 140 0.0001 nan 0.0500 0.0000
## 160 0.0001 nan 0.0500 -0.0000
## 180 0.0000 nan 0.0500 -0.0000
## 200 0.0000 nan 0.0500 0.0000
##
## - Fold10: shrinkage=0.05, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold10: shrinkage=0.05, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0414 nan 0.0500 0.0027
## 2 0.0383 nan 0.0500 0.0031
## 3 0.0358 nan 0.0500 0.0022
## 4 0.0328 nan 0.0500 0.0016
## 5 0.0316 nan 0.0500 -0.0013
## 6 0.0295 nan 0.0500 0.0023
## 7 0.0277 nan 0.0500 0.0013
## 8 0.0263 nan 0.0500 0.0004
## 9 0.0240 nan 0.0500 0.0015
## 10 0.0225 nan 0.0500 0.0018
## 20 0.0121 nan 0.0500 0.0003
## 40 0.0043 nan 0.0500 0.0000
## 60 0.0020 nan 0.0500 -0.0000
## 80 0.0011 nan 0.0500 -0.0000
## 100 0.0006 nan 0.0500 0.0000
## 120 0.0004 nan 0.0500 -0.0000
## 140 0.0002 nan 0.0500 -0.0000
## 160 0.0001 nan 0.0500 -0.0000
## 180 0.0001 nan 0.0500 -0.0000
## 200 0.0001 nan 0.0500 0.0000
##
## - Fold10: shrinkage=0.05, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold10: shrinkage=0.05, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0417 nan 0.0500 0.0019
## 2 0.0397 nan 0.0500 0.0019
## 3 0.0377 nan 0.0500 0.0016
## 4 0.0351 nan 0.0500 0.0025
## 5 0.0332 nan 0.0500 0.0023
## 6 0.0319 nan 0.0500 0.0008
## 7 0.0299 nan 0.0500 0.0017
## 8 0.0278 nan 0.0500 0.0016
## 9 0.0270 nan 0.0500 -0.0005
## 10 0.0259 nan 0.0500 0.0002
## 20 0.0164 nan 0.0500 -0.0002
## 40 0.0094 nan 0.0500 0.0001
## 60 0.0058 nan 0.0500 0.0001
## 80 0.0038 nan 0.0500 0.0000
## 100 0.0024 nan 0.0500 0.0000
## 120 0.0019 nan 0.0500 -0.0001
## 140 0.0013 nan 0.0500 -0.0000
## 160 0.0009 nan 0.0500 -0.0000
## 180 0.0006 nan 0.0500 -0.0000
## 200 0.0004 nan 0.0500 0.0000
##
## - Fold10: shrinkage=0.05, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold10: shrinkage=0.05, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0411 nan 0.0500 0.0015
## 2 0.0401 nan 0.0500 -0.0004
## 3 0.0384 nan 0.0500 0.0011
## 4 0.0351 nan 0.0500 0.0019
## 5 0.0331 nan 0.0500 0.0010
## 6 0.0302 nan 0.0500 0.0017
## 7 0.0279 nan 0.0500 0.0013
## 8 0.0262 nan 0.0500 0.0001
## 9 0.0241 nan 0.0500 0.0013
## 10 0.0220 nan 0.0500 0.0016
## 20 0.0108 nan 0.0500 0.0006
## 40 0.0033 nan 0.0500 0.0001
## 60 0.0012 nan 0.0500 -0.0000
## 80 0.0005 nan 0.0500 -0.0000
## 100 0.0002 nan 0.0500 -0.0000
## 120 0.0001 nan 0.0500 -0.0000
## 140 0.0000 nan 0.0500 -0.0000
## 160 0.0000 nan 0.0500 -0.0000
## 180 0.0000 nan 0.0500 -0.0000
## 200 0.0000 nan 0.0500 0.0000
##
## - Fold10: shrinkage=0.05, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold10: shrinkage=0.05, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0407 nan 0.0500 0.0023
## 2 0.0377 nan 0.0500 0.0021
## 3 0.0347 nan 0.0500 0.0015
## 4 0.0321 nan 0.0500 0.0013
## 5 0.0292 nan 0.0500 0.0020
## 6 0.0279 nan 0.0500 -0.0010
## 7 0.0260 nan 0.0500 0.0017
## 8 0.0238 nan 0.0500 0.0019
## 9 0.0217 nan 0.0500 0.0009
## 10 0.0200 nan 0.0500 0.0016
## 20 0.0114 nan 0.0500 0.0007
## 40 0.0045 nan 0.0500 -0.0001
## 60 0.0022 nan 0.0500 -0.0000
## 80 0.0012 nan 0.0500 -0.0000
## 100 0.0007 nan 0.0500 -0.0000
## 120 0.0004 nan 0.0500 -0.0000
## 140 0.0002 nan 0.0500 0.0000
## 160 0.0002 nan 0.0500 -0.0000
## 180 0.0001 nan 0.0500 -0.0000
## 200 0.0001 nan 0.0500 -0.0000
##
## - Fold10: shrinkage=0.05, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold10: shrinkage=0.05, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0417 nan 0.0500 0.0025
## 2 0.0394 nan 0.0500 0.0020
## 3 0.0378 nan 0.0500 0.0007
## 4 0.0356 nan 0.0500 0.0024
## 5 0.0336 nan 0.0500 0.0016
## 6 0.0315 nan 0.0500 0.0019
## 7 0.0302 nan 0.0500 0.0000
## 8 0.0282 nan 0.0500 0.0018
## 9 0.0264 nan 0.0500 0.0014
## 10 0.0248 nan 0.0500 0.0013
## 20 0.0156 nan 0.0500 0.0007
## 40 0.0082 nan 0.0500 0.0002
## 60 0.0052 nan 0.0500 0.0001
## 80 0.0035 nan 0.0500 -0.0001
## 100 0.0022 nan 0.0500 0.0000
## 120 0.0015 nan 0.0500 -0.0000
## 140 0.0011 nan 0.0500 -0.0000
## 160 0.0008 nan 0.0500 -0.0000
## 180 0.0006 nan 0.0500 0.0000
## 200 0.0005 nan 0.0500 -0.0000
##
## - Fold10: shrinkage=0.05, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold10: shrinkage=0.10, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0387 nan 0.1000 0.0012
## 2 0.0335 nan 0.1000 0.0047
## 3 0.0313 nan 0.1000 0.0005
## 4 0.0277 nan 0.1000 0.0008
## 5 0.0259 nan 0.1000 0.0007
## 6 0.0225 nan 0.1000 0.0014
## 7 0.0203 nan 0.1000 0.0006
## 8 0.0185 nan 0.1000 0.0016
## 9 0.0170 nan 0.1000 0.0005
## 10 0.0158 nan 0.1000 0.0010
## 20 0.0070 nan 0.1000 -0.0002
## 40 0.0019 nan 0.1000 -0.0000
## 60 0.0006 nan 0.1000 0.0000
## 80 0.0002 nan 0.1000 -0.0000
## 100 0.0001 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold10: shrinkage=0.10, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold10: shrinkage=0.10, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0383 nan 0.1000 0.0041
## 2 0.0338 nan 0.1000 0.0017
## 3 0.0317 nan 0.1000 -0.0001
## 4 0.0275 nan 0.1000 0.0030
## 5 0.0246 nan 0.1000 0.0020
## 6 0.0224 nan 0.1000 0.0016
## 7 0.0200 nan 0.1000 0.0024
## 8 0.0188 nan 0.1000 0.0003
## 9 0.0174 nan 0.1000 0.0006
## 10 0.0163 nan 0.1000 0.0009
## 20 0.0070 nan 0.1000 0.0003
## 40 0.0019 nan 0.1000 0.0000
## 60 0.0008 nan 0.1000 -0.0000
## 80 0.0004 nan 0.1000 -0.0000
## 100 0.0002 nan 0.1000 0.0000
## 120 0.0001 nan 0.1000 0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold10: shrinkage=0.10, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold10: shrinkage=0.10, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0385 nan 0.1000 0.0048
## 2 0.0349 nan 0.1000 0.0025
## 3 0.0315 nan 0.1000 0.0036
## 4 0.0289 nan 0.1000 0.0017
## 5 0.0258 nan 0.1000 0.0011
## 6 0.0233 nan 0.1000 0.0022
## 7 0.0215 nan 0.1000 0.0020
## 8 0.0206 nan 0.1000 -0.0002
## 9 0.0184 nan 0.1000 0.0011
## 10 0.0174 nan 0.1000 -0.0001
## 20 0.0098 nan 0.1000 0.0004
## 40 0.0039 nan 0.1000 -0.0001
## 60 0.0020 nan 0.1000 0.0000
## 80 0.0010 nan 0.1000 -0.0000
## 100 0.0006 nan 0.1000 -0.0000
## 120 0.0004 nan 0.1000 0.0000
## 140 0.0003 nan 0.1000 -0.0000
## 160 0.0002 nan 0.1000 0.0000
## 180 0.0001 nan 0.1000 -0.0000
## 200 0.0001 nan 0.1000 -0.0000
##
## - Fold10: shrinkage=0.10, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold10: shrinkage=0.10, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0377 nan 0.1000 0.0054
## 2 0.0321 nan 0.1000 0.0054
## 3 0.0280 nan 0.1000 0.0030
## 4 0.0233 nan 0.1000 0.0032
## 5 0.0201 nan 0.1000 0.0035
## 6 0.0183 nan 0.1000 0.0013
## 7 0.0165 nan 0.1000 0.0016
## 8 0.0148 nan 0.1000 0.0014
## 9 0.0131 nan 0.1000 0.0023
## 10 0.0120 nan 0.1000 0.0008
## 20 0.0041 nan 0.1000 0.0002
## 40 0.0009 nan 0.1000 -0.0000
## 60 0.0002 nan 0.1000 -0.0000
## 80 0.0000 nan 0.1000 0.0000
## 100 0.0000 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold10: shrinkage=0.10, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold10: shrinkage=0.10, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0365 nan 0.1000 0.0060
## 2 0.0312 nan 0.1000 0.0052
## 3 0.0278 nan 0.1000 -0.0011
## 4 0.0248 nan 0.1000 0.0018
## 5 0.0216 nan 0.1000 0.0015
## 6 0.0180 nan 0.1000 0.0024
## 7 0.0159 nan 0.1000 0.0014
## 8 0.0149 nan 0.1000 0.0001
## 9 0.0130 nan 0.1000 0.0011
## 10 0.0111 nan 0.1000 0.0019
## 20 0.0037 nan 0.1000 0.0002
## 40 0.0010 nan 0.1000 -0.0000
## 60 0.0004 nan 0.1000 0.0000
## 80 0.0002 nan 0.1000 0.0000
## 100 0.0001 nan 0.1000 0.0000
## 120 0.0001 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold10: shrinkage=0.10, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold10: shrinkage=0.10, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0382 nan 0.1000 0.0024
## 2 0.0345 nan 0.1000 0.0030
## 3 0.0306 nan 0.1000 0.0041
## 4 0.0281 nan 0.1000 0.0011
## 5 0.0266 nan 0.1000 -0.0007
## 6 0.0252 nan 0.1000 0.0004
## 7 0.0228 nan 0.1000 0.0016
## 8 0.0213 nan 0.1000 0.0009
## 9 0.0201 nan 0.1000 0.0009
## 10 0.0176 nan 0.1000 0.0018
## 20 0.0099 nan 0.1000 -0.0003
## 40 0.0042 nan 0.1000 0.0000
## 60 0.0018 nan 0.1000 -0.0000
## 80 0.0008 nan 0.1000 0.0000
## 100 0.0004 nan 0.1000 0.0000
## 120 0.0002 nan 0.1000 -0.0000
## 140 0.0001 nan 0.1000 -0.0000
## 160 0.0001 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold10: shrinkage=0.10, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold10: shrinkage=0.10, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0386 nan 0.1000 0.0028
## 2 0.0340 nan 0.1000 0.0026
## 3 0.0286 nan 0.1000 0.0021
## 4 0.0258 nan 0.1000 0.0000
## 5 0.0210 nan 0.1000 0.0034
## 6 0.0181 nan 0.1000 0.0027
## 7 0.0163 nan 0.1000 0.0004
## 8 0.0144 nan 0.1000 0.0016
## 9 0.0126 nan 0.1000 0.0012
## 10 0.0108 nan 0.1000 0.0009
## 20 0.0037 nan 0.1000 -0.0001
## 40 0.0007 nan 0.1000 0.0001
## 60 0.0001 nan 0.1000 -0.0000
## 80 0.0000 nan 0.1000 0.0000
## 100 0.0000 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold10: shrinkage=0.10, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold10: shrinkage=0.10, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0365 nan 0.1000 0.0048
## 2 0.0319 nan 0.1000 0.0016
## 3 0.0299 nan 0.1000 0.0014
## 4 0.0255 nan 0.1000 0.0042
## 5 0.0218 nan 0.1000 0.0037
## 6 0.0184 nan 0.1000 0.0018
## 7 0.0171 nan 0.1000 0.0008
## 8 0.0154 nan 0.1000 0.0014
## 9 0.0133 nan 0.1000 0.0019
## 10 0.0117 nan 0.1000 0.0018
## 20 0.0040 nan 0.1000 0.0004
## 40 0.0008 nan 0.1000 0.0000
## 60 0.0003 nan 0.1000 -0.0000
## 80 0.0001 nan 0.1000 -0.0000
## 100 0.0000 nan 0.1000 0.0000
## 120 0.0000 nan 0.1000 0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold10: shrinkage=0.10, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold10: shrinkage=0.10, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0378 nan 0.1000 0.0058
## 2 0.0329 nan 0.1000 0.0042
## 3 0.0287 nan 0.1000 0.0038
## 4 0.0254 nan 0.1000 0.0028
## 5 0.0238 nan 0.1000 0.0007
## 6 0.0218 nan 0.1000 0.0017
## 7 0.0204 nan 0.1000 0.0006
## 8 0.0200 nan 0.1000 -0.0013
## 9 0.0189 nan 0.1000 -0.0006
## 10 0.0178 nan 0.1000 0.0013
## 20 0.0116 nan 0.1000 -0.0003
## 40 0.0043 nan 0.1000 0.0001
## 60 0.0022 nan 0.1000 -0.0001
## 80 0.0009 nan 0.1000 0.0000
## 100 0.0005 nan 0.1000 -0.0000
## 120 0.0003 nan 0.1000 0.0000
## 140 0.0002 nan 0.1000 -0.0000
## 160 0.0001 nan 0.1000 -0.0000
## 180 0.0001 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold10: shrinkage=0.10, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold11: shrinkage=0.01, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0425 nan 0.0100 0.0004
## 2 0.0420 nan 0.0100 0.0003
## 3 0.0417 nan 0.0100 0.0003
## 4 0.0411 nan 0.0100 0.0006
## 5 0.0410 nan 0.0100 -0.0002
## 6 0.0406 nan 0.0100 0.0002
## 7 0.0400 nan 0.0100 0.0004
## 8 0.0395 nan 0.0100 0.0003
## 9 0.0389 nan 0.0100 0.0005
## 10 0.0384 nan 0.0100 0.0005
## 20 0.0343 nan 0.0100 0.0002
## 40 0.0270 nan 0.0100 0.0003
## 60 0.0219 nan 0.0100 -0.0000
## 80 0.0180 nan 0.0100 0.0001
## 100 0.0150 nan 0.0100 -0.0000
## 120 0.0123 nan 0.0100 -0.0000
## 140 0.0102 nan 0.0100 0.0001
## 160 0.0086 nan 0.0100 0.0001
## 180 0.0073 nan 0.0100 0.0000
## 200 0.0062 nan 0.0100 0.0001
##
## - Fold11: shrinkage=0.01, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold11: shrinkage=0.01, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0425 nan 0.0100 0.0005
## 2 0.0421 nan 0.0100 0.0002
## 3 0.0416 nan 0.0100 0.0002
## 4 0.0411 nan 0.0100 0.0004
## 5 0.0406 nan 0.0100 0.0005
## 6 0.0403 nan 0.0100 0.0004
## 7 0.0397 nan 0.0100 0.0003
## 8 0.0392 nan 0.0100 0.0005
## 9 0.0387 nan 0.0100 0.0005
## 10 0.0381 nan 0.0100 0.0005
## 20 0.0338 nan 0.0100 0.0004
## 40 0.0278 nan 0.0100 0.0002
## 60 0.0224 nan 0.0100 0.0000
## 80 0.0182 nan 0.0100 0.0000
## 100 0.0154 nan 0.0100 0.0001
## 120 0.0132 nan 0.0100 0.0001
## 140 0.0111 nan 0.0100 0.0001
## 160 0.0096 nan 0.0100 0.0000
## 180 0.0081 nan 0.0100 -0.0000
## 200 0.0069 nan 0.0100 0.0000
##
## - Fold11: shrinkage=0.01, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold11: shrinkage=0.01, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0425 nan 0.0100 0.0004
## 2 0.0421 nan 0.0100 -0.0000
## 3 0.0417 nan 0.0100 0.0004
## 4 0.0412 nan 0.0100 0.0005
## 5 0.0407 nan 0.0100 0.0005
## 6 0.0402 nan 0.0100 0.0005
## 7 0.0397 nan 0.0100 0.0004
## 8 0.0393 nan 0.0100 0.0004
## 9 0.0391 nan 0.0100 0.0001
## 10 0.0386 nan 0.0100 0.0005
## 20 0.0345 nan 0.0100 0.0004
## 40 0.0278 nan 0.0100 0.0001
## 60 0.0230 nan 0.0100 -0.0001
## 80 0.0192 nan 0.0100 0.0001
## 100 0.0165 nan 0.0100 0.0001
## 120 0.0143 nan 0.0100 0.0000
## 140 0.0128 nan 0.0100 0.0000
## 160 0.0112 nan 0.0100 0.0000
## 180 0.0097 nan 0.0100 0.0000
## 200 0.0089 nan 0.0100 0.0000
##
## - Fold11: shrinkage=0.01, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold11: shrinkage=0.01, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0424 nan 0.0100 0.0003
## 2 0.0418 nan 0.0100 0.0004
## 3 0.0412 nan 0.0100 0.0007
## 4 0.0406 nan 0.0100 0.0006
## 5 0.0399 nan 0.0100 0.0005
## 6 0.0393 nan 0.0100 0.0007
## 7 0.0386 nan 0.0100 0.0005
## 8 0.0380 nan 0.0100 0.0005
## 9 0.0373 nan 0.0100 0.0005
## 10 0.0368 nan 0.0100 0.0006
## 20 0.0327 nan 0.0100 0.0003
## 40 0.0252 nan 0.0100 0.0002
## 60 0.0190 nan 0.0100 0.0002
## 80 0.0147 nan 0.0100 0.0000
## 100 0.0115 nan 0.0100 0.0001
## 120 0.0092 nan 0.0100 0.0000
## 140 0.0073 nan 0.0100 0.0000
## 160 0.0057 nan 0.0100 0.0000
## 180 0.0047 nan 0.0100 0.0001
## 200 0.0039 nan 0.0100 0.0000
##
## - Fold11: shrinkage=0.01, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold11: shrinkage=0.01, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0425 nan 0.0100 0.0003
## 2 0.0419 nan 0.0100 0.0005
## 3 0.0414 nan 0.0100 0.0005
## 4 0.0411 nan 0.0100 0.0003
## 5 0.0404 nan 0.0100 0.0007
## 6 0.0398 nan 0.0100 0.0006
## 7 0.0394 nan 0.0100 0.0002
## 8 0.0392 nan 0.0100 -0.0001
## 9 0.0388 nan 0.0100 -0.0000
## 10 0.0383 nan 0.0100 0.0006
## 20 0.0332 nan 0.0100 0.0001
## 40 0.0253 nan 0.0100 0.0005
## 60 0.0193 nan 0.0100 -0.0000
## 80 0.0155 nan 0.0100 0.0001
## 100 0.0124 nan 0.0100 0.0001
## 120 0.0098 nan 0.0100 0.0001
## 140 0.0079 nan 0.0100 0.0000
## 160 0.0063 nan 0.0100 0.0000
## 180 0.0050 nan 0.0100 0.0000
## 200 0.0041 nan 0.0100 0.0000
##
## - Fold11: shrinkage=0.01, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold11: shrinkage=0.01, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0426 nan 0.0100 0.0004
## 2 0.0422 nan 0.0100 0.0001
## 3 0.0418 nan 0.0100 0.0005
## 4 0.0412 nan 0.0100 0.0006
## 5 0.0409 nan 0.0100 0.0001
## 6 0.0406 nan 0.0100 0.0002
## 7 0.0401 nan 0.0100 0.0003
## 8 0.0396 nan 0.0100 0.0003
## 9 0.0390 nan 0.0100 0.0004
## 10 0.0386 nan 0.0100 -0.0000
## 20 0.0341 nan 0.0100 0.0003
## 40 0.0267 nan 0.0100 0.0002
## 60 0.0218 nan 0.0100 0.0002
## 80 0.0180 nan 0.0100 -0.0000
## 100 0.0154 nan 0.0100 0.0001
## 120 0.0132 nan 0.0100 0.0001
## 140 0.0117 nan 0.0100 0.0001
## 160 0.0103 nan 0.0100 0.0000
## 180 0.0090 nan 0.0100 0.0000
## 200 0.0080 nan 0.0100 0.0000
##
## - Fold11: shrinkage=0.01, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold11: shrinkage=0.01, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0424 nan 0.0100 0.0006
## 2 0.0416 nan 0.0100 0.0005
## 3 0.0411 nan 0.0100 0.0004
## 4 0.0405 nan 0.0100 0.0006
## 5 0.0401 nan 0.0100 0.0000
## 6 0.0396 nan 0.0100 0.0002
## 7 0.0389 nan 0.0100 0.0005
## 8 0.0386 nan 0.0100 0.0001
## 9 0.0380 nan 0.0100 0.0004
## 10 0.0374 nan 0.0100 0.0004
## 20 0.0329 nan 0.0100 0.0003
## 40 0.0242 nan 0.0100 0.0001
## 60 0.0184 nan 0.0100 0.0001
## 80 0.0142 nan 0.0100 0.0001
## 100 0.0106 nan 0.0100 0.0001
## 120 0.0083 nan 0.0100 0.0001
## 140 0.0065 nan 0.0100 0.0000
## 160 0.0052 nan 0.0100 0.0000
## 180 0.0041 nan 0.0100 0.0000
## 200 0.0033 nan 0.0100 -0.0000
##
## - Fold11: shrinkage=0.01, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold11: shrinkage=0.01, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0424 nan 0.0100 0.0005
## 2 0.0416 nan 0.0100 0.0006
## 3 0.0410 nan 0.0100 0.0005
## 4 0.0405 nan 0.0100 0.0004
## 5 0.0400 nan 0.0100 0.0005
## 6 0.0394 nan 0.0100 0.0006
## 7 0.0388 nan 0.0100 0.0005
## 8 0.0381 nan 0.0100 0.0006
## 9 0.0376 nan 0.0100 0.0005
## 10 0.0369 nan 0.0100 0.0005
## 20 0.0322 nan 0.0100 0.0002
## 40 0.0248 nan 0.0100 0.0003
## 60 0.0187 nan 0.0100 0.0000
## 80 0.0149 nan 0.0100 0.0001
## 100 0.0115 nan 0.0100 0.0001
## 120 0.0092 nan 0.0100 0.0000
## 140 0.0075 nan 0.0100 0.0000
## 160 0.0061 nan 0.0100 0.0000
## 180 0.0051 nan 0.0100 -0.0000
## 200 0.0043 nan 0.0100 0.0000
##
## - Fold11: shrinkage=0.01, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold11: shrinkage=0.01, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0426 nan 0.0100 0.0003
## 2 0.0421 nan 0.0100 0.0002
## 3 0.0417 nan 0.0100 0.0003
## 4 0.0411 nan 0.0100 0.0005
## 5 0.0406 nan 0.0100 0.0005
## 6 0.0400 nan 0.0100 0.0004
## 7 0.0394 nan 0.0100 0.0006
## 8 0.0388 nan 0.0100 0.0004
## 9 0.0382 nan 0.0100 0.0005
## 10 0.0379 nan 0.0100 0.0002
## 20 0.0334 nan 0.0100 0.0003
## 40 0.0275 nan 0.0100 0.0001
## 60 0.0231 nan 0.0100 0.0002
## 80 0.0192 nan 0.0100 0.0002
## 100 0.0161 nan 0.0100 0.0001
## 120 0.0135 nan 0.0100 0.0001
## 140 0.0118 nan 0.0100 0.0001
## 160 0.0104 nan 0.0100 -0.0000
## 180 0.0090 nan 0.0100 0.0000
## 200 0.0083 nan 0.0100 -0.0000
##
## - Fold11: shrinkage=0.01, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold11: shrinkage=0.05, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0405 nan 0.0500 0.0027
## 2 0.0382 nan 0.0500 0.0016
## 3 0.0356 nan 0.0500 0.0020
## 4 0.0333 nan 0.0500 0.0021
## 5 0.0318 nan 0.0500 0.0015
## 6 0.0296 nan 0.0500 0.0016
## 7 0.0287 nan 0.0500 0.0002
## 8 0.0268 nan 0.0500 0.0018
## 9 0.0256 nan 0.0500 -0.0001
## 10 0.0244 nan 0.0500 0.0011
## 20 0.0145 nan 0.0500 0.0006
## 40 0.0064 nan 0.0500 0.0000
## 60 0.0028 nan 0.0500 -0.0000
## 80 0.0015 nan 0.0500 0.0000
## 100 0.0009 nan 0.0500 0.0000
## 120 0.0005 nan 0.0500 0.0000
## 140 0.0004 nan 0.0500 0.0000
## 160 0.0002 nan 0.0500 -0.0000
## 180 0.0001 nan 0.0500 -0.0000
## 200 0.0001 nan 0.0500 -0.0000
##
## - Fold11: shrinkage=0.05, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold11: shrinkage=0.05, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0413 nan 0.0500 0.0008
## 2 0.0388 nan 0.0500 0.0020
## 3 0.0367 nan 0.0500 0.0010
## 4 0.0346 nan 0.0500 0.0015
## 5 0.0326 nan 0.0500 0.0019
## 6 0.0308 nan 0.0500 0.0018
## 7 0.0284 nan 0.0500 0.0011
## 8 0.0274 nan 0.0500 -0.0001
## 9 0.0254 nan 0.0500 0.0016
## 10 0.0244 nan 0.0500 0.0000
## 20 0.0149 nan 0.0500 0.0002
## 40 0.0062 nan 0.0500 -0.0001
## 60 0.0037 nan 0.0500 -0.0000
## 80 0.0022 nan 0.0500 -0.0001
## 100 0.0012 nan 0.0500 -0.0000
## 120 0.0007 nan 0.0500 -0.0000
## 140 0.0005 nan 0.0500 -0.0000
## 160 0.0003 nan 0.0500 0.0000
## 180 0.0002 nan 0.0500 0.0000
## 200 0.0001 nan 0.0500 -0.0000
##
## - Fold11: shrinkage=0.05, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold11: shrinkage=0.05, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0405 nan 0.0500 0.0025
## 2 0.0385 nan 0.0500 0.0013
## 3 0.0356 nan 0.0500 0.0025
## 4 0.0338 nan 0.0500 0.0020
## 5 0.0318 nan 0.0500 0.0018
## 6 0.0302 nan 0.0500 0.0018
## 7 0.0286 nan 0.0500 0.0014
## 8 0.0268 nan 0.0500 0.0017
## 9 0.0258 nan 0.0500 0.0003
## 10 0.0248 nan 0.0500 0.0001
## 20 0.0161 nan 0.0500 0.0007
## 40 0.0085 nan 0.0500 0.0003
## 60 0.0052 nan 0.0500 -0.0001
## 80 0.0033 nan 0.0500 0.0000
## 100 0.0025 nan 0.0500 -0.0000
## 120 0.0019 nan 0.0500 -0.0000
## 140 0.0013 nan 0.0500 0.0000
## 160 0.0010 nan 0.0500 -0.0000
## 180 0.0008 nan 0.0500 0.0000
## 200 0.0006 nan 0.0500 -0.0000
##
## - Fold11: shrinkage=0.05, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold11: shrinkage=0.05, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0402 nan 0.0500 0.0017
## 2 0.0370 nan 0.0500 0.0033
## 3 0.0340 nan 0.0500 0.0025
## 4 0.0314 nan 0.0500 0.0019
## 5 0.0296 nan 0.0500 0.0015
## 6 0.0280 nan 0.0500 0.0016
## 7 0.0258 nan 0.0500 0.0019
## 8 0.0243 nan 0.0500 0.0011
## 9 0.0228 nan 0.0500 0.0010
## 10 0.0213 nan 0.0500 0.0018
## 20 0.0108 nan 0.0500 0.0005
## 40 0.0040 nan 0.0500 0.0002
## 60 0.0015 nan 0.0500 0.0001
## 80 0.0006 nan 0.0500 -0.0000
## 100 0.0003 nan 0.0500 0.0000
## 120 0.0002 nan 0.0500 -0.0000
## 140 0.0001 nan 0.0500 0.0000
## 160 0.0000 nan 0.0500 0.0000
## 180 0.0000 nan 0.0500 -0.0000
## 200 0.0000 nan 0.0500 -0.0000
##
## - Fold11: shrinkage=0.05, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold11: shrinkage=0.05, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0401 nan 0.0500 0.0029
## 2 0.0380 nan 0.0500 0.0018
## 3 0.0367 nan 0.0500 0.0012
## 4 0.0337 nan 0.0500 0.0024
## 5 0.0316 nan 0.0500 0.0019
## 6 0.0294 nan 0.0500 0.0014
## 7 0.0268 nan 0.0500 0.0018
## 8 0.0256 nan 0.0500 0.0012
## 9 0.0236 nan 0.0500 0.0017
## 10 0.0222 nan 0.0500 0.0014
## 20 0.0130 nan 0.0500 0.0007
## 40 0.0046 nan 0.0500 0.0001
## 60 0.0020 nan 0.0500 0.0000
## 80 0.0010 nan 0.0500 0.0000
## 100 0.0005 nan 0.0500 0.0000
## 120 0.0003 nan 0.0500 -0.0000
## 140 0.0002 nan 0.0500 0.0000
## 160 0.0001 nan 0.0500 -0.0000
## 180 0.0001 nan 0.0500 -0.0000
## 200 0.0001 nan 0.0500 -0.0000
##
## - Fold11: shrinkage=0.05, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold11: shrinkage=0.05, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0409 nan 0.0500 0.0014
## 2 0.0387 nan 0.0500 0.0015
## 3 0.0365 nan 0.0500 0.0025
## 4 0.0346 nan 0.0500 0.0006
## 5 0.0332 nan 0.0500 0.0010
## 6 0.0319 nan 0.0500 0.0010
## 7 0.0294 nan 0.0500 0.0015
## 8 0.0284 nan 0.0500 0.0008
## 9 0.0277 nan 0.0500 -0.0000
## 10 0.0265 nan 0.0500 0.0014
## 20 0.0168 nan 0.0500 0.0000
## 40 0.0084 nan 0.0500 0.0001
## 60 0.0049 nan 0.0500 -0.0001
## 80 0.0031 nan 0.0500 0.0001
## 100 0.0022 nan 0.0500 -0.0000
## 120 0.0015 nan 0.0500 0.0000
## 140 0.0010 nan 0.0500 0.0000
## 160 0.0007 nan 0.0500 -0.0000
## 180 0.0005 nan 0.0500 -0.0000
## 200 0.0003 nan 0.0500 -0.0000
##
## - Fold11: shrinkage=0.05, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold11: shrinkage=0.05, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0399 nan 0.0500 0.0023
## 2 0.0370 nan 0.0500 0.0024
## 3 0.0340 nan 0.0500 0.0029
## 4 0.0318 nan 0.0500 0.0002
## 5 0.0291 nan 0.0500 0.0025
## 6 0.0271 nan 0.0500 0.0013
## 7 0.0257 nan 0.0500 0.0014
## 8 0.0244 nan 0.0500 0.0014
## 9 0.0227 nan 0.0500 0.0011
## 10 0.0208 nan 0.0500 0.0017
## 20 0.0097 nan 0.0500 0.0007
## 40 0.0028 nan 0.0500 0.0000
## 60 0.0011 nan 0.0500 0.0000
## 80 0.0004 nan 0.0500 -0.0000
## 100 0.0002 nan 0.0500 -0.0000
## 120 0.0001 nan 0.0500 0.0000
## 140 0.0000 nan 0.0500 -0.0000
## 160 0.0000 nan 0.0500 -0.0000
## 180 0.0000 nan 0.0500 0.0000
## 200 0.0000 nan 0.0500 -0.0000
##
## - Fold11: shrinkage=0.05, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold11: shrinkage=0.05, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0407 nan 0.0500 0.0017
## 2 0.0382 nan 0.0500 0.0018
## 3 0.0358 nan 0.0500 0.0020
## 4 0.0327 nan 0.0500 0.0014
## 5 0.0310 nan 0.0500 0.0006
## 6 0.0298 nan 0.0500 0.0005
## 7 0.0274 nan 0.0500 0.0027
## 8 0.0256 nan 0.0500 0.0005
## 9 0.0240 nan 0.0500 0.0013
## 10 0.0231 nan 0.0500 0.0007
## 20 0.0129 nan 0.0500 0.0008
## 40 0.0052 nan 0.0500 0.0002
## 60 0.0021 nan 0.0500 -0.0000
## 80 0.0011 nan 0.0500 0.0000
## 100 0.0007 nan 0.0500 -0.0000
## 120 0.0005 nan 0.0500 0.0000
## 140 0.0004 nan 0.0500 -0.0000
## 160 0.0003 nan 0.0500 -0.0000
## 180 0.0002 nan 0.0500 -0.0000
## 200 0.0001 nan 0.0500 -0.0000
##
## - Fold11: shrinkage=0.05, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold11: shrinkage=0.05, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0412 nan 0.0500 0.0012
## 2 0.0388 nan 0.0500 0.0020
## 3 0.0380 nan 0.0500 -0.0005
## 4 0.0362 nan 0.0500 0.0013
## 5 0.0352 nan 0.0500 -0.0016
## 6 0.0327 nan 0.0500 0.0021
## 7 0.0314 nan 0.0500 0.0010
## 8 0.0298 nan 0.0500 0.0012
## 9 0.0277 nan 0.0500 0.0014
## 10 0.0261 nan 0.0500 0.0014
## 20 0.0164 nan 0.0500 0.0006
## 40 0.0078 nan 0.0500 0.0002
## 60 0.0050 nan 0.0500 -0.0000
## 80 0.0034 nan 0.0500 -0.0000
## 100 0.0021 nan 0.0500 0.0000
## 120 0.0013 nan 0.0500 0.0000
## 140 0.0010 nan 0.0500 -0.0000
## 160 0.0007 nan 0.0500 -0.0000
## 180 0.0005 nan 0.0500 -0.0000
## 200 0.0004 nan 0.0500 -0.0000
##
## - Fold11: shrinkage=0.05, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold11: shrinkage=0.10, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0372 nan 0.1000 0.0034
## 2 0.0338 nan 0.1000 0.0029
## 3 0.0317 nan 0.1000 0.0010
## 4 0.0306 nan 0.1000 -0.0004
## 5 0.0266 nan 0.1000 0.0035
## 6 0.0230 nan 0.1000 0.0021
## 7 0.0212 nan 0.1000 0.0016
## 8 0.0207 nan 0.1000 0.0000
## 9 0.0185 nan 0.1000 0.0017
## 10 0.0171 nan 0.1000 0.0009
## 20 0.0072 nan 0.1000 -0.0014
## 40 0.0023 nan 0.1000 -0.0001
## 60 0.0008 nan 0.1000 -0.0000
## 80 0.0003 nan 0.1000 0.0000
## 100 0.0001 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold11: shrinkage=0.10, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold11: shrinkage=0.10, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0371 nan 0.1000 0.0051
## 2 0.0323 nan 0.1000 0.0041
## 3 0.0289 nan 0.1000 0.0032
## 4 0.0257 nan 0.1000 0.0035
## 5 0.0244 nan 0.1000 -0.0004
## 6 0.0207 nan 0.1000 0.0020
## 7 0.0193 nan 0.1000 0.0012
## 8 0.0180 nan 0.1000 0.0015
## 9 0.0157 nan 0.1000 0.0005
## 10 0.0146 nan 0.1000 -0.0000
## 20 0.0078 nan 0.1000 -0.0005
## 40 0.0026 nan 0.1000 -0.0003
## 60 0.0012 nan 0.1000 0.0001
## 80 0.0005 nan 0.1000 -0.0000
## 100 0.0003 nan 0.1000 -0.0000
## 120 0.0001 nan 0.1000 -0.0000
## 140 0.0001 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold11: shrinkage=0.10, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold11: shrinkage=0.10, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0398 nan 0.1000 0.0004
## 2 0.0365 nan 0.1000 0.0028
## 3 0.0323 nan 0.1000 0.0038
## 4 0.0287 nan 0.1000 0.0035
## 5 0.0269 nan 0.1000 0.0010
## 6 0.0244 nan 0.1000 0.0026
## 7 0.0221 nan 0.1000 0.0017
## 8 0.0197 nan 0.1000 0.0011
## 9 0.0180 nan 0.1000 0.0017
## 10 0.0168 nan 0.1000 -0.0002
## 20 0.0099 nan 0.1000 0.0005
## 40 0.0036 nan 0.1000 0.0002
## 60 0.0015 nan 0.1000 -0.0000
## 80 0.0008 nan 0.1000 0.0000
## 100 0.0004 nan 0.1000 -0.0000
## 120 0.0002 nan 0.1000 -0.0000
## 140 0.0001 nan 0.1000 -0.0000
## 160 0.0001 nan 0.1000 -0.0000
## 180 0.0001 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 0.0000
##
## - Fold11: shrinkage=0.10, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold11: shrinkage=0.10, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0369 nan 0.1000 0.0021
## 2 0.0337 nan 0.1000 0.0017
## 3 0.0285 nan 0.1000 0.0033
## 4 0.0240 nan 0.1000 0.0027
## 5 0.0202 nan 0.1000 0.0031
## 6 0.0182 nan 0.1000 0.0014
## 7 0.0158 nan 0.1000 0.0018
## 8 0.0143 nan 0.1000 0.0001
## 9 0.0139 nan 0.1000 -0.0003
## 10 0.0115 nan 0.1000 0.0016
## 20 0.0041 nan 0.1000 -0.0001
## 40 0.0007 nan 0.1000 0.0000
## 60 0.0002 nan 0.1000 0.0000
## 80 0.0001 nan 0.1000 -0.0000
## 100 0.0000 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold11: shrinkage=0.10, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold11: shrinkage=0.10, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0368 nan 0.1000 0.0073
## 2 0.0328 nan 0.1000 0.0036
## 3 0.0280 nan 0.1000 0.0040
## 4 0.0241 nan 0.1000 0.0023
## 5 0.0227 nan 0.1000 0.0004
## 6 0.0214 nan 0.1000 0.0010
## 7 0.0186 nan 0.1000 0.0022
## 8 0.0160 nan 0.1000 0.0017
## 9 0.0140 nan 0.1000 0.0013
## 10 0.0123 nan 0.1000 0.0014
## 20 0.0044 nan 0.1000 0.0004
## 40 0.0010 nan 0.1000 -0.0000
## 60 0.0004 nan 0.1000 -0.0000
## 80 0.0002 nan 0.1000 -0.0000
## 100 0.0001 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold11: shrinkage=0.10, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold11: shrinkage=0.10, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0365 nan 0.1000 0.0046
## 2 0.0310 nan 0.1000 0.0047
## 3 0.0285 nan 0.1000 0.0013
## 4 0.0252 nan 0.1000 0.0033
## 5 0.0233 nan 0.1000 0.0017
## 6 0.0216 nan 0.1000 0.0010
## 7 0.0193 nan 0.1000 0.0023
## 8 0.0170 nan 0.1000 0.0014
## 9 0.0154 nan 0.1000 0.0006
## 10 0.0146 nan 0.1000 -0.0001
## 20 0.0072 nan 0.1000 -0.0002
## 40 0.0027 nan 0.1000 0.0001
## 60 0.0013 nan 0.1000 -0.0001
## 80 0.0006 nan 0.1000 -0.0000
## 100 0.0004 nan 0.1000 -0.0000
## 120 0.0002 nan 0.1000 0.0000
## 140 0.0001 nan 0.1000 0.0000
## 160 0.0001 nan 0.1000 -0.0000
## 180 0.0001 nan 0.1000 -0.0000
## 200 0.0001 nan 0.1000 -0.0000
##
## - Fold11: shrinkage=0.10, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold11: shrinkage=0.10, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0387 nan 0.1000 -0.0001
## 2 0.0327 nan 0.1000 0.0021
## 3 0.0287 nan 0.1000 0.0045
## 4 0.0246 nan 0.1000 0.0033
## 5 0.0209 nan 0.1000 0.0015
## 6 0.0179 nan 0.1000 0.0026
## 7 0.0165 nan 0.1000 -0.0005
## 8 0.0142 nan 0.1000 0.0018
## 9 0.0124 nan 0.1000 0.0011
## 10 0.0109 nan 0.1000 0.0017
## 20 0.0029 nan 0.1000 0.0000
## 40 0.0006 nan 0.1000 -0.0000
## 60 0.0002 nan 0.1000 0.0000
## 80 0.0000 nan 0.1000 -0.0000
## 100 0.0000 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold11: shrinkage=0.10, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold11: shrinkage=0.10, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0380 nan 0.1000 0.0046
## 2 0.0325 nan 0.1000 0.0048
## 3 0.0289 nan 0.1000 0.0036
## 4 0.0243 nan 0.1000 0.0026
## 5 0.0215 nan 0.1000 0.0017
## 6 0.0188 nan 0.1000 0.0012
## 7 0.0168 nan 0.1000 0.0002
## 8 0.0140 nan 0.1000 0.0016
## 9 0.0119 nan 0.1000 0.0019
## 10 0.0110 nan 0.1000 0.0002
## 20 0.0045 nan 0.1000 0.0001
## 40 0.0010 nan 0.1000 -0.0001
## 60 0.0005 nan 0.1000 0.0000
## 80 0.0003 nan 0.1000 -0.0000
## 100 0.0002 nan 0.1000 0.0000
## 120 0.0001 nan 0.1000 -0.0000
## 140 0.0001 nan 0.1000 0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 0.0000
##
## - Fold11: shrinkage=0.10, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold11: shrinkage=0.10, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0382 nan 0.1000 0.0010
## 2 0.0345 nan 0.1000 0.0014
## 3 0.0310 nan 0.1000 0.0036
## 4 0.0277 nan 0.1000 0.0030
## 5 0.0242 nan 0.1000 0.0029
## 6 0.0219 nan 0.1000 0.0024
## 7 0.0209 nan 0.1000 0.0006
## 8 0.0190 nan 0.1000 0.0015
## 9 0.0171 nan 0.1000 0.0017
## 10 0.0165 nan 0.1000 -0.0006
## 20 0.0096 nan 0.1000 -0.0004
## 40 0.0040 nan 0.1000 -0.0001
## 60 0.0016 nan 0.1000 0.0001
## 80 0.0008 nan 0.1000 0.0000
## 100 0.0004 nan 0.1000 0.0000
## 120 0.0003 nan 0.1000 0.0000
## 140 0.0002 nan 0.1000 0.0000
## 160 0.0001 nan 0.1000 -0.0000
## 180 0.0001 nan 0.1000 -0.0000
## 200 0.0001 nan 0.1000 -0.0000
##
## - Fold11: shrinkage=0.10, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold12: shrinkage=0.01, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0435 nan 0.0100 0.0006
## 2 0.0430 nan 0.0100 0.0004
## 3 0.0425 nan 0.0100 0.0005
## 4 0.0423 nan 0.0100 0.0001
## 5 0.0417 nan 0.0100 0.0005
## 6 0.0412 nan 0.0100 0.0006
## 7 0.0408 nan 0.0100 0.0003
## 8 0.0402 nan 0.0100 0.0002
## 9 0.0395 nan 0.0100 0.0005
## 10 0.0390 nan 0.0100 0.0003
## 20 0.0350 nan 0.0100 0.0004
## 40 0.0283 nan 0.0100 0.0003
## 60 0.0227 nan 0.0100 0.0001
## 80 0.0183 nan 0.0100 0.0001
## 100 0.0151 nan 0.0100 0.0001
## 120 0.0122 nan 0.0100 0.0001
## 140 0.0102 nan 0.0100 0.0001
## 160 0.0085 nan 0.0100 0.0000
## 180 0.0073 nan 0.0100 0.0000
## 200 0.0063 nan 0.0100 -0.0000
##
## - Fold12: shrinkage=0.01, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold12: shrinkage=0.01, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0436 nan 0.0100 0.0001
## 2 0.0431 nan 0.0100 0.0003
## 3 0.0425 nan 0.0100 0.0006
## 4 0.0421 nan 0.0100 0.0005
## 5 0.0414 nan 0.0100 0.0006
## 6 0.0409 nan 0.0100 0.0000
## 7 0.0404 nan 0.0100 0.0005
## 8 0.0399 nan 0.0100 0.0005
## 9 0.0394 nan 0.0100 0.0005
## 10 0.0390 nan 0.0100 0.0005
## 20 0.0350 nan 0.0100 0.0005
## 40 0.0282 nan 0.0100 0.0000
## 60 0.0229 nan 0.0100 0.0002
## 80 0.0183 nan 0.0100 0.0002
## 100 0.0152 nan 0.0100 0.0001
## 120 0.0125 nan 0.0100 0.0001
## 140 0.0105 nan 0.0100 0.0000
## 160 0.0089 nan 0.0100 0.0001
## 180 0.0074 nan 0.0100 -0.0000
## 200 0.0062 nan 0.0100 0.0000
##
## - Fold12: shrinkage=0.01, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold12: shrinkage=0.01, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0436 nan 0.0100 0.0006
## 2 0.0429 nan 0.0100 0.0006
## 3 0.0423 nan 0.0100 0.0006
## 4 0.0418 nan 0.0100 0.0001
## 5 0.0413 nan 0.0100 0.0005
## 6 0.0411 nan 0.0100 -0.0000
## 7 0.0406 nan 0.0100 0.0004
## 8 0.0401 nan 0.0100 0.0001
## 9 0.0396 nan 0.0100 0.0003
## 10 0.0391 nan 0.0100 0.0005
## 20 0.0347 nan 0.0100 0.0004
## 40 0.0278 nan 0.0100 0.0003
## 60 0.0228 nan 0.0100 0.0003
## 80 0.0192 nan 0.0100 0.0001
## 100 0.0162 nan 0.0100 0.0001
## 120 0.0138 nan 0.0100 0.0001
## 140 0.0120 nan 0.0100 -0.0000
## 160 0.0103 nan 0.0100 0.0001
## 180 0.0091 nan 0.0100 0.0000
## 200 0.0079 nan 0.0100 0.0000
##
## - Fold12: shrinkage=0.01, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold12: shrinkage=0.01, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0433 nan 0.0100 0.0004
## 2 0.0425 nan 0.0100 0.0006
## 3 0.0421 nan 0.0100 0.0001
## 4 0.0415 nan 0.0100 0.0005
## 5 0.0407 nan 0.0100 0.0006
## 6 0.0402 nan 0.0100 0.0004
## 7 0.0399 nan 0.0100 0.0000
## 8 0.0392 nan 0.0100 0.0004
## 9 0.0385 nan 0.0100 0.0005
## 10 0.0378 nan 0.0100 0.0005
## 20 0.0326 nan 0.0100 0.0005
## 40 0.0242 nan 0.0100 0.0003
## 60 0.0189 nan 0.0100 0.0002
## 80 0.0148 nan 0.0100 0.0002
## 100 0.0116 nan 0.0100 0.0001
## 120 0.0091 nan 0.0100 0.0001
## 140 0.0074 nan 0.0100 0.0001
## 160 0.0059 nan 0.0100 0.0001
## 180 0.0048 nan 0.0100 0.0000
## 200 0.0040 nan 0.0100 0.0000
##
## - Fold12: shrinkage=0.01, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold12: shrinkage=0.01, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0435 nan 0.0100 0.0005
## 2 0.0426 nan 0.0100 0.0008
## 3 0.0421 nan 0.0100 0.0004
## 4 0.0416 nan 0.0100 0.0005
## 5 0.0411 nan 0.0100 0.0004
## 6 0.0406 nan 0.0100 0.0004
## 7 0.0398 nan 0.0100 0.0006
## 8 0.0395 nan 0.0100 0.0000
## 9 0.0388 nan 0.0100 0.0007
## 10 0.0381 nan 0.0100 0.0005
## 20 0.0333 nan 0.0100 0.0005
## 40 0.0257 nan 0.0100 0.0000
## 60 0.0198 nan 0.0100 0.0002
## 80 0.0154 nan 0.0100 0.0001
## 100 0.0121 nan 0.0100 0.0001
## 120 0.0097 nan 0.0100 -0.0000
## 140 0.0078 nan 0.0100 -0.0000
## 160 0.0064 nan 0.0100 0.0000
## 180 0.0052 nan 0.0100 0.0000
## 200 0.0043 nan 0.0100 0.0000
##
## - Fold12: shrinkage=0.01, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold12: shrinkage=0.01, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0436 nan 0.0100 0.0004
## 2 0.0429 nan 0.0100 0.0006
## 3 0.0425 nan 0.0100 0.0003
## 4 0.0422 nan 0.0100 0.0001
## 5 0.0416 nan 0.0100 0.0005
## 6 0.0412 nan 0.0100 0.0003
## 7 0.0407 nan 0.0100 0.0003
## 8 0.0401 nan 0.0100 0.0005
## 9 0.0396 nan 0.0100 0.0005
## 10 0.0391 nan 0.0100 0.0005
## 20 0.0350 nan 0.0100 0.0004
## 40 0.0284 nan 0.0100 0.0003
## 60 0.0229 nan 0.0100 0.0002
## 80 0.0191 nan 0.0100 0.0002
## 100 0.0161 nan 0.0100 0.0002
## 120 0.0137 nan 0.0100 -0.0000
## 140 0.0115 nan 0.0100 -0.0000
## 160 0.0099 nan 0.0100 0.0000
## 180 0.0088 nan 0.0100 -0.0001
## 200 0.0078 nan 0.0100 0.0001
##
## - Fold12: shrinkage=0.01, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold12: shrinkage=0.01, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0434 nan 0.0100 0.0006
## 2 0.0427 nan 0.0100 0.0004
## 3 0.0420 nan 0.0100 0.0006
## 4 0.0412 nan 0.0100 0.0006
## 5 0.0404 nan 0.0100 0.0008
## 6 0.0397 nan 0.0100 0.0007
## 7 0.0391 nan 0.0100 0.0004
## 8 0.0384 nan 0.0100 0.0006
## 9 0.0378 nan 0.0100 0.0006
## 10 0.0373 nan 0.0100 0.0005
## 20 0.0319 nan 0.0100 0.0004
## 40 0.0240 nan 0.0100 0.0004
## 60 0.0180 nan 0.0100 -0.0000
## 80 0.0141 nan 0.0100 0.0002
## 100 0.0113 nan 0.0100 0.0000
## 120 0.0086 nan 0.0100 0.0001
## 140 0.0066 nan 0.0100 0.0001
## 160 0.0052 nan 0.0100 0.0000
## 180 0.0042 nan 0.0100 0.0000
## 200 0.0033 nan 0.0100 0.0000
##
## - Fold12: shrinkage=0.01, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold12: shrinkage=0.01, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0432 nan 0.0100 0.0008
## 2 0.0427 nan 0.0100 0.0005
## 3 0.0422 nan 0.0100 0.0005
## 4 0.0415 nan 0.0100 0.0003
## 5 0.0409 nan 0.0100 0.0005
## 6 0.0406 nan 0.0100 0.0002
## 7 0.0399 nan 0.0100 0.0006
## 8 0.0393 nan 0.0100 0.0006
## 9 0.0386 nan 0.0100 0.0005
## 10 0.0381 nan 0.0100 0.0005
## 20 0.0330 nan 0.0100 0.0004
## 40 0.0256 nan 0.0100 0.0003
## 60 0.0191 nan 0.0100 0.0003
## 80 0.0155 nan 0.0100 0.0002
## 100 0.0120 nan 0.0100 0.0001
## 120 0.0097 nan 0.0100 0.0001
## 140 0.0079 nan 0.0100 0.0000
## 160 0.0065 nan 0.0100 0.0000
## 180 0.0053 nan 0.0100 0.0001
## 200 0.0044 nan 0.0100 0.0000
##
## - Fold12: shrinkage=0.01, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold12: shrinkage=0.01, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0434 nan 0.0100 0.0006
## 2 0.0428 nan 0.0100 0.0004
## 3 0.0423 nan 0.0100 0.0003
## 4 0.0417 nan 0.0100 0.0004
## 5 0.0414 nan 0.0100 0.0002
## 6 0.0410 nan 0.0100 0.0001
## 7 0.0405 nan 0.0100 0.0004
## 8 0.0400 nan 0.0100 0.0005
## 9 0.0399 nan 0.0100 -0.0002
## 10 0.0393 nan 0.0100 0.0005
## 20 0.0345 nan 0.0100 0.0003
## 40 0.0275 nan 0.0100 0.0003
## 60 0.0225 nan 0.0100 0.0002
## 80 0.0188 nan 0.0100 0.0002
## 100 0.0158 nan 0.0100 0.0001
## 120 0.0133 nan 0.0100 0.0001
## 140 0.0115 nan 0.0100 0.0001
## 160 0.0102 nan 0.0100 -0.0000
## 180 0.0089 nan 0.0100 0.0000
## 200 0.0079 nan 0.0100 0.0000
##
## - Fold12: shrinkage=0.01, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold12: shrinkage=0.05, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0415 nan 0.0500 0.0025
## 2 0.0390 nan 0.0500 0.0026
## 3 0.0370 nan 0.0500 0.0020
## 4 0.0359 nan 0.0500 -0.0004
## 5 0.0329 nan 0.0500 0.0023
## 6 0.0305 nan 0.0500 0.0016
## 7 0.0287 nan 0.0500 0.0015
## 8 0.0266 nan 0.0500 0.0012
## 9 0.0251 nan 0.0500 0.0015
## 10 0.0236 nan 0.0500 0.0016
## 20 0.0142 nan 0.0500 0.0002
## 40 0.0058 nan 0.0500 0.0002
## 60 0.0027 nan 0.0500 0.0000
## 80 0.0014 nan 0.0500 0.0000
## 100 0.0008 nan 0.0500 -0.0000
## 120 0.0005 nan 0.0500 -0.0000
## 140 0.0003 nan 0.0500 -0.0000
## 160 0.0002 nan 0.0500 0.0000
## 180 0.0001 nan 0.0500 0.0000
## 200 0.0001 nan 0.0500 -0.0000
##
## - Fold12: shrinkage=0.05, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold12: shrinkage=0.05, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0405 nan 0.0500 0.0030
## 2 0.0381 nan 0.0500 0.0025
## 3 0.0362 nan 0.0500 0.0016
## 4 0.0336 nan 0.0500 0.0022
## 5 0.0312 nan 0.0500 0.0018
## 6 0.0303 nan 0.0500 0.0005
## 7 0.0285 nan 0.0500 0.0016
## 8 0.0267 nan 0.0500 0.0018
## 9 0.0250 nan 0.0500 0.0016
## 10 0.0236 nan 0.0500 0.0010
## 20 0.0140 nan 0.0500 0.0007
## 40 0.0057 nan 0.0500 0.0003
## 60 0.0030 nan 0.0500 0.0001
## 80 0.0016 nan 0.0500 -0.0001
## 100 0.0010 nan 0.0500 0.0000
## 120 0.0006 nan 0.0500 -0.0000
## 140 0.0004 nan 0.0500 -0.0000
## 160 0.0003 nan 0.0500 -0.0000
## 180 0.0002 nan 0.0500 -0.0000
## 200 0.0001 nan 0.0500 0.0000
##
## - Fold12: shrinkage=0.05, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold12: shrinkage=0.05, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0420 nan 0.0500 0.0026
## 2 0.0385 nan 0.0500 0.0027
## 3 0.0372 nan 0.0500 0.0005
## 4 0.0361 nan 0.0500 0.0004
## 5 0.0347 nan 0.0500 0.0010
## 6 0.0333 nan 0.0500 0.0014
## 7 0.0325 nan 0.0500 0.0001
## 8 0.0305 nan 0.0500 0.0010
## 9 0.0291 nan 0.0500 0.0010
## 10 0.0276 nan 0.0500 0.0008
## 20 0.0177 nan 0.0500 0.0001
## 40 0.0081 nan 0.0500 -0.0001
## 60 0.0044 nan 0.0500 -0.0001
## 80 0.0030 nan 0.0500 -0.0001
## 100 0.0021 nan 0.0500 -0.0000
## 120 0.0015 nan 0.0500 0.0000
## 140 0.0010 nan 0.0500 -0.0000
## 160 0.0008 nan 0.0500 -0.0000
## 180 0.0006 nan 0.0500 -0.0000
## 200 0.0004 nan 0.0500 0.0000
##
## - Fold12: shrinkage=0.05, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold12: shrinkage=0.05, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0407 nan 0.0500 0.0034
## 2 0.0378 nan 0.0500 0.0013
## 3 0.0352 nan 0.0500 0.0021
## 4 0.0329 nan 0.0500 0.0016
## 5 0.0307 nan 0.0500 0.0016
## 6 0.0284 nan 0.0500 0.0021
## 7 0.0274 nan 0.0500 0.0007
## 8 0.0251 nan 0.0500 0.0017
## 9 0.0235 nan 0.0500 0.0013
## 10 0.0223 nan 0.0500 0.0003
## 20 0.0117 nan 0.0500 0.0007
## 40 0.0039 nan 0.0500 0.0001
## 60 0.0017 nan 0.0500 -0.0000
## 80 0.0007 nan 0.0500 0.0000
## 100 0.0004 nan 0.0500 -0.0000
## 120 0.0002 nan 0.0500 0.0000
## 140 0.0001 nan 0.0500 -0.0000
## 160 0.0000 nan 0.0500 -0.0000
## 180 0.0000 nan 0.0500 0.0000
## 200 0.0000 nan 0.0500 -0.0000
##
## - Fold12: shrinkage=0.05, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold12: shrinkage=0.05, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0422 nan 0.0500 0.0011
## 2 0.0390 nan 0.0500 0.0025
## 3 0.0376 nan 0.0500 0.0010
## 4 0.0353 nan 0.0500 0.0022
## 5 0.0326 nan 0.0500 0.0028
## 6 0.0300 nan 0.0500 0.0021
## 7 0.0281 nan 0.0500 0.0020
## 8 0.0255 nan 0.0500 0.0014
## 9 0.0234 nan 0.0500 0.0012
## 10 0.0224 nan 0.0500 0.0003
## 20 0.0121 nan 0.0500 0.0005
## 40 0.0042 nan 0.0500 -0.0000
## 60 0.0021 nan 0.0500 -0.0000
## 80 0.0012 nan 0.0500 0.0000
## 100 0.0006 nan 0.0500 -0.0000
## 120 0.0004 nan 0.0500 0.0000
## 140 0.0003 nan 0.0500 -0.0000
## 160 0.0002 nan 0.0500 -0.0000
## 180 0.0001 nan 0.0500 -0.0000
## 200 0.0001 nan 0.0500 -0.0000
##
## - Fold12: shrinkage=0.05, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold12: shrinkage=0.05, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0406 nan 0.0500 0.0028
## 2 0.0385 nan 0.0500 0.0014
## 3 0.0365 nan 0.0500 0.0020
## 4 0.0346 nan 0.0500 0.0009
## 5 0.0320 nan 0.0500 0.0013
## 6 0.0301 nan 0.0500 0.0010
## 7 0.0286 nan 0.0500 0.0006
## 8 0.0270 nan 0.0500 0.0009
## 9 0.0251 nan 0.0500 0.0015
## 10 0.0245 nan 0.0500 0.0000
## 20 0.0159 nan 0.0500 0.0007
## 40 0.0088 nan 0.0500 0.0000
## 60 0.0052 nan 0.0500 0.0001
## 80 0.0039 nan 0.0500 -0.0000
## 100 0.0027 nan 0.0500 0.0000
## 120 0.0018 nan 0.0500 -0.0000
## 140 0.0012 nan 0.0500 -0.0000
## 160 0.0009 nan 0.0500 -0.0000
## 180 0.0007 nan 0.0500 0.0000
## 200 0.0005 nan 0.0500 0.0000
##
## - Fold12: shrinkage=0.05, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold12: shrinkage=0.05, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0411 nan 0.0500 0.0027
## 2 0.0391 nan 0.0500 0.0010
## 3 0.0376 nan 0.0500 0.0010
## 4 0.0347 nan 0.0500 0.0020
## 5 0.0329 nan 0.0500 0.0022
## 6 0.0305 nan 0.0500 0.0021
## 7 0.0278 nan 0.0500 0.0013
## 8 0.0254 nan 0.0500 0.0016
## 9 0.0234 nan 0.0500 0.0015
## 10 0.0220 nan 0.0500 0.0001
## 20 0.0108 nan 0.0500 0.0007
## 40 0.0033 nan 0.0500 -0.0000
## 60 0.0012 nan 0.0500 -0.0000
## 80 0.0005 nan 0.0500 -0.0000
## 100 0.0002 nan 0.0500 0.0000
## 120 0.0001 nan 0.0500 -0.0000
## 140 0.0000 nan 0.0500 0.0000
## 160 0.0000 nan 0.0500 0.0000
## 180 0.0000 nan 0.0500 -0.0000
## 200 0.0000 nan 0.0500 -0.0000
##
## - Fold12: shrinkage=0.05, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold12: shrinkage=0.05, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0405 nan 0.0500 0.0021
## 2 0.0382 nan 0.0500 0.0024
## 3 0.0350 nan 0.0500 0.0015
## 4 0.0323 nan 0.0500 0.0028
## 5 0.0307 nan 0.0500 0.0005
## 6 0.0298 nan 0.0500 -0.0005
## 7 0.0277 nan 0.0500 0.0022
## 8 0.0257 nan 0.0500 0.0014
## 9 0.0239 nan 0.0500 0.0016
## 10 0.0220 nan 0.0500 0.0019
## 20 0.0124 nan 0.0500 0.0003
## 40 0.0046 nan 0.0500 -0.0002
## 60 0.0023 nan 0.0500 0.0001
## 80 0.0013 nan 0.0500 0.0000
## 100 0.0009 nan 0.0500 0.0000
## 120 0.0006 nan 0.0500 -0.0000
## 140 0.0005 nan 0.0500 -0.0000
## 160 0.0003 nan 0.0500 0.0000
## 180 0.0002 nan 0.0500 0.0000
## 200 0.0002 nan 0.0500 -0.0000
##
## - Fold12: shrinkage=0.05, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold12: shrinkage=0.05, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0416 nan 0.0500 0.0025
## 2 0.0398 nan 0.0500 0.0019
## 3 0.0371 nan 0.0500 0.0017
## 4 0.0345 nan 0.0500 0.0024
## 5 0.0323 nan 0.0500 0.0006
## 6 0.0307 nan 0.0500 0.0015
## 7 0.0293 nan 0.0500 0.0011
## 8 0.0275 nan 0.0500 0.0019
## 9 0.0256 nan 0.0500 0.0016
## 10 0.0248 nan 0.0500 0.0005
## 20 0.0149 nan 0.0500 0.0006
## 40 0.0075 nan 0.0500 0.0001
## 60 0.0039 nan 0.0500 -0.0000
## 80 0.0024 nan 0.0500 -0.0000
## 100 0.0016 nan 0.0500 0.0000
## 120 0.0011 nan 0.0500 -0.0000
## 140 0.0007 nan 0.0500 -0.0000
## 160 0.0005 nan 0.0500 -0.0000
## 180 0.0004 nan 0.0500 -0.0000
## 200 0.0003 nan 0.0500 -0.0000
##
## - Fold12: shrinkage=0.05, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold12: shrinkage=0.10, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0413 nan 0.1000 -0.0022
## 2 0.0380 nan 0.1000 0.0027
## 3 0.0340 nan 0.1000 0.0042
## 4 0.0317 nan 0.1000 0.0013
## 5 0.0279 nan 0.1000 0.0032
## 6 0.0241 nan 0.1000 0.0033
## 7 0.0224 nan 0.1000 0.0001
## 8 0.0204 nan 0.1000 0.0013
## 9 0.0188 nan 0.1000 0.0021
## 10 0.0170 nan 0.1000 0.0007
## 20 0.0061 nan 0.1000 0.0009
## 40 0.0014 nan 0.1000 -0.0000
## 60 0.0006 nan 0.1000 -0.0000
## 80 0.0002 nan 0.1000 -0.0000
## 100 0.0001 nan 0.1000 -0.0000
## 120 0.0001 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold12: shrinkage=0.10, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold12: shrinkage=0.10, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0371 nan 0.1000 0.0045
## 2 0.0316 nan 0.1000 0.0046
## 3 0.0289 nan 0.1000 -0.0003
## 4 0.0271 nan 0.1000 0.0014
## 5 0.0245 nan 0.1000 0.0020
## 6 0.0233 nan 0.1000 0.0011
## 7 0.0214 nan 0.1000 0.0020
## 8 0.0188 nan 0.1000 0.0012
## 9 0.0166 nan 0.1000 0.0011
## 10 0.0152 nan 0.1000 -0.0005
## 20 0.0073 nan 0.1000 -0.0002
## 40 0.0027 nan 0.1000 -0.0000
## 60 0.0010 nan 0.1000 -0.0001
## 80 0.0004 nan 0.1000 -0.0000
## 100 0.0001 nan 0.1000 0.0000
## 120 0.0001 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold12: shrinkage=0.10, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold12: shrinkage=0.10, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0375 nan 0.1000 0.0057
## 2 0.0358 nan 0.1000 -0.0006
## 3 0.0335 nan 0.1000 0.0024
## 4 0.0306 nan 0.1000 0.0020
## 5 0.0281 nan 0.1000 0.0032
## 6 0.0256 nan 0.1000 0.0011
## 7 0.0239 nan 0.1000 0.0011
## 8 0.0216 nan 0.1000 0.0019
## 9 0.0200 nan 0.1000 0.0011
## 10 0.0180 nan 0.1000 0.0019
## 20 0.0093 nan 0.1000 0.0005
## 40 0.0035 nan 0.1000 -0.0002
## 60 0.0020 nan 0.1000 -0.0001
## 80 0.0011 nan 0.1000 -0.0000
## 100 0.0007 nan 0.1000 -0.0000
## 120 0.0004 nan 0.1000 -0.0000
## 140 0.0002 nan 0.1000 -0.0000
## 160 0.0002 nan 0.1000 -0.0000
## 180 0.0001 nan 0.1000 0.0000
## 200 0.0001 nan 0.1000 -0.0000
##
## - Fold12: shrinkage=0.10, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold12: shrinkage=0.10, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0366 nan 0.1000 0.0076
## 2 0.0324 nan 0.1000 0.0020
## 3 0.0264 nan 0.1000 0.0049
## 4 0.0241 nan 0.1000 0.0024
## 5 0.0217 nan 0.1000 0.0022
## 6 0.0189 nan 0.1000 0.0010
## 7 0.0166 nan 0.1000 0.0022
## 8 0.0146 nan 0.1000 0.0011
## 9 0.0133 nan 0.1000 0.0007
## 10 0.0113 nan 0.1000 0.0013
## 20 0.0035 nan 0.1000 0.0001
## 40 0.0006 nan 0.1000 0.0000
## 60 0.0002 nan 0.1000 0.0000
## 80 0.0000 nan 0.1000 -0.0000
## 100 0.0000 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold12: shrinkage=0.10, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold12: shrinkage=0.10, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0375 nan 0.1000 0.0066
## 2 0.0314 nan 0.1000 0.0047
## 3 0.0269 nan 0.1000 0.0025
## 4 0.0240 nan 0.1000 0.0024
## 5 0.0220 nan 0.1000 0.0001
## 6 0.0193 nan 0.1000 0.0028
## 7 0.0162 nan 0.1000 0.0022
## 8 0.0145 nan 0.1000 0.0010
## 9 0.0127 nan 0.1000 0.0010
## 10 0.0107 nan 0.1000 0.0009
## 20 0.0046 nan 0.1000 0.0005
## 40 0.0009 nan 0.1000 -0.0000
## 60 0.0004 nan 0.1000 -0.0000
## 80 0.0002 nan 0.1000 0.0000
## 100 0.0001 nan 0.1000 0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold12: shrinkage=0.10, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold12: shrinkage=0.10, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0413 nan 0.1000 0.0017
## 2 0.0360 nan 0.1000 0.0053
## 3 0.0314 nan 0.1000 0.0033
## 4 0.0281 nan 0.1000 0.0005
## 5 0.0250 nan 0.1000 0.0031
## 6 0.0220 nan 0.1000 0.0026
## 7 0.0201 nan 0.1000 0.0024
## 8 0.0182 nan 0.1000 0.0021
## 9 0.0164 nan 0.1000 0.0019
## 10 0.0160 nan 0.1000 -0.0007
## 20 0.0079 nan 0.1000 0.0005
## 40 0.0028 nan 0.1000 -0.0002
## 60 0.0014 nan 0.1000 -0.0001
## 80 0.0006 nan 0.1000 -0.0000
## 100 0.0004 nan 0.1000 0.0000
## 120 0.0002 nan 0.1000 -0.0000
## 140 0.0001 nan 0.1000 -0.0000
## 160 0.0001 nan 0.1000 -0.0000
## 180 0.0001 nan 0.1000 -0.0000
## 200 0.0001 nan 0.1000 -0.0000
##
## - Fold12: shrinkage=0.10, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold12: shrinkage=0.10, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0374 nan 0.1000 0.0025
## 2 0.0331 nan 0.1000 0.0042
## 3 0.0275 nan 0.1000 0.0034
## 4 0.0251 nan 0.1000 0.0015
## 5 0.0224 nan 0.1000 0.0025
## 6 0.0194 nan 0.1000 0.0027
## 7 0.0173 nan 0.1000 0.0010
## 8 0.0153 nan 0.1000 0.0010
## 9 0.0137 nan 0.1000 0.0014
## 10 0.0125 nan 0.1000 0.0015
## 20 0.0041 nan 0.1000 -0.0001
## 40 0.0006 nan 0.1000 -0.0000
## 60 0.0001 nan 0.1000 -0.0000
## 80 0.0000 nan 0.1000 -0.0000
## 100 0.0000 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold12: shrinkage=0.10, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold12: shrinkage=0.10, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0373 nan 0.1000 0.0059
## 2 0.0313 nan 0.1000 0.0020
## 3 0.0271 nan 0.1000 0.0047
## 4 0.0247 nan 0.1000 0.0027
## 5 0.0223 nan 0.1000 0.0023
## 6 0.0195 nan 0.1000 0.0028
## 7 0.0175 nan 0.1000 0.0017
## 8 0.0161 nan 0.1000 0.0003
## 9 0.0136 nan 0.1000 0.0007
## 10 0.0122 nan 0.1000 0.0016
## 20 0.0041 nan 0.1000 0.0002
## 40 0.0010 nan 0.1000 -0.0001
## 60 0.0003 nan 0.1000 0.0000
## 80 0.0001 nan 0.1000 0.0000
## 100 0.0000 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold12: shrinkage=0.10, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold12: shrinkage=0.10, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0388 nan 0.1000 0.0051
## 2 0.0342 nan 0.1000 0.0046
## 3 0.0310 nan 0.1000 0.0029
## 4 0.0283 nan 0.1000 0.0019
## 5 0.0251 nan 0.1000 0.0022
## 6 0.0229 nan 0.1000 0.0027
## 7 0.0210 nan 0.1000 0.0011
## 8 0.0193 nan 0.1000 0.0019
## 9 0.0181 nan 0.1000 0.0016
## 10 0.0169 nan 0.1000 0.0009
## 20 0.0090 nan 0.1000 -0.0000
## 40 0.0035 nan 0.1000 0.0001
## 60 0.0018 nan 0.1000 -0.0000
## 80 0.0008 nan 0.1000 -0.0000
## 100 0.0005 nan 0.1000 -0.0000
## 120 0.0003 nan 0.1000 -0.0000
## 140 0.0002 nan 0.1000 -0.0000
## 160 0.0001 nan 0.1000 -0.0000
## 180 0.0001 nan 0.1000 -0.0000
## 200 0.0001 nan 0.1000 -0.0000
##
## - Fold12: shrinkage=0.10, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold13: shrinkage=0.01, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0438 nan 0.0100 0.0006
## 2 0.0432 nan 0.0100 0.0004
## 3 0.0426 nan 0.0100 0.0005
## 4 0.0419 nan 0.0100 0.0006
## 5 0.0415 nan 0.0100 0.0004
## 6 0.0410 nan 0.0100 0.0004
## 7 0.0404 nan 0.0100 0.0006
## 8 0.0398 nan 0.0100 0.0006
## 9 0.0393 nan 0.0100 0.0006
## 10 0.0388 nan 0.0100 0.0003
## 20 0.0351 nan 0.0100 0.0004
## 40 0.0275 nan 0.0100 0.0000
## 60 0.0223 nan 0.0100 0.0001
## 80 0.0181 nan 0.0100 0.0002
## 100 0.0151 nan 0.0100 0.0001
## 120 0.0126 nan 0.0100 0.0001
## 140 0.0104 nan 0.0100 0.0002
## 160 0.0087 nan 0.0100 0.0001
## 180 0.0073 nan 0.0100 0.0000
## 200 0.0064 nan 0.0100 0.0000
##
## - Fold13: shrinkage=0.01, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold13: shrinkage=0.01, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0438 nan 0.0100 0.0007
## 2 0.0431 nan 0.0100 0.0006
## 3 0.0426 nan 0.0100 0.0006
## 4 0.0422 nan 0.0100 0.0004
## 5 0.0417 nan 0.0100 0.0005
## 6 0.0414 nan 0.0100 0.0000
## 7 0.0412 nan 0.0100 -0.0000
## 8 0.0406 nan 0.0100 0.0005
## 9 0.0400 nan 0.0100 0.0005
## 10 0.0395 nan 0.0100 0.0005
## 20 0.0349 nan 0.0100 0.0004
## 40 0.0276 nan 0.0100 0.0003
## 60 0.0224 nan 0.0100 0.0002
## 80 0.0186 nan 0.0100 0.0002
## 100 0.0155 nan 0.0100 0.0001
## 120 0.0127 nan 0.0100 0.0001
## 140 0.0106 nan 0.0100 0.0001
## 160 0.0090 nan 0.0100 0.0000
## 180 0.0077 nan 0.0100 0.0001
## 200 0.0066 nan 0.0100 0.0000
##
## - Fold13: shrinkage=0.01, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold13: shrinkage=0.01, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0438 nan 0.0100 0.0006
## 2 0.0431 nan 0.0100 0.0006
## 3 0.0425 nan 0.0100 0.0006
## 4 0.0422 nan 0.0100 0.0003
## 5 0.0416 nan 0.0100 0.0006
## 6 0.0410 nan 0.0100 0.0006
## 7 0.0404 nan 0.0100 0.0002
## 8 0.0399 nan 0.0100 0.0006
## 9 0.0394 nan 0.0100 0.0005
## 10 0.0388 nan 0.0100 0.0003
## 20 0.0350 nan 0.0100 0.0004
## 40 0.0283 nan 0.0100 0.0003
## 60 0.0227 nan 0.0100 0.0001
## 80 0.0191 nan 0.0100 -0.0000
## 100 0.0159 nan 0.0100 0.0001
## 120 0.0137 nan 0.0100 0.0001
## 140 0.0115 nan 0.0100 0.0000
## 160 0.0102 nan 0.0100 0.0000
## 180 0.0089 nan 0.0100 0.0000
## 200 0.0080 nan 0.0100 0.0000
##
## - Fold13: shrinkage=0.01, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold13: shrinkage=0.01, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0438 nan 0.0100 0.0004
## 2 0.0430 nan 0.0100 0.0005
## 3 0.0425 nan 0.0100 0.0002
## 4 0.0422 nan 0.0100 -0.0000
## 5 0.0416 nan 0.0100 0.0007
## 6 0.0410 nan 0.0100 0.0004
## 7 0.0404 nan 0.0100 0.0004
## 8 0.0397 nan 0.0100 0.0007
## 9 0.0392 nan 0.0100 0.0004
## 10 0.0386 nan 0.0100 0.0002
## 20 0.0342 nan 0.0100 0.0001
## 40 0.0264 nan 0.0100 0.0005
## 60 0.0206 nan 0.0100 0.0002
## 80 0.0158 nan 0.0100 0.0000
## 100 0.0122 nan 0.0100 0.0001
## 120 0.0097 nan 0.0100 0.0001
## 140 0.0077 nan 0.0100 0.0000
## 160 0.0062 nan 0.0100 0.0001
## 180 0.0050 nan 0.0100 -0.0000
## 200 0.0040 nan 0.0100 0.0001
##
## - Fold13: shrinkage=0.01, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold13: shrinkage=0.01, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0441 nan 0.0100 0.0001
## 2 0.0434 nan 0.0100 0.0003
## 3 0.0428 nan 0.0100 0.0004
## 4 0.0421 nan 0.0100 0.0007
## 5 0.0417 nan 0.0100 0.0002
## 6 0.0411 nan 0.0100 0.0005
## 7 0.0404 nan 0.0100 0.0006
## 8 0.0400 nan 0.0100 0.0004
## 9 0.0393 nan 0.0100 0.0006
## 10 0.0389 nan 0.0100 0.0003
## 20 0.0342 nan 0.0100 0.0005
## 40 0.0263 nan 0.0100 0.0004
## 60 0.0202 nan 0.0100 0.0002
## 80 0.0156 nan 0.0100 0.0000
## 100 0.0122 nan 0.0100 0.0001
## 120 0.0098 nan 0.0100 0.0001
## 140 0.0078 nan 0.0100 0.0001
## 160 0.0063 nan 0.0100 0.0000
## 180 0.0051 nan 0.0100 0.0000
## 200 0.0042 nan 0.0100 0.0000
##
## - Fold13: shrinkage=0.01, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold13: shrinkage=0.01, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0443 nan 0.0100 -0.0001
## 2 0.0438 nan 0.0100 0.0005
## 3 0.0431 nan 0.0100 0.0005
## 4 0.0425 nan 0.0100 0.0003
## 5 0.0418 nan 0.0100 0.0005
## 6 0.0412 nan 0.0100 0.0005
## 7 0.0408 nan 0.0100 0.0004
## 8 0.0402 nan 0.0100 0.0005
## 9 0.0399 nan 0.0100 0.0001
## 10 0.0395 nan 0.0100 0.0003
## 20 0.0350 nan 0.0100 0.0003
## 40 0.0278 nan 0.0100 0.0003
## 60 0.0222 nan 0.0100 0.0002
## 80 0.0182 nan 0.0100 0.0000
## 100 0.0154 nan 0.0100 0.0001
## 120 0.0132 nan 0.0100 0.0000
## 140 0.0114 nan 0.0100 0.0000
## 160 0.0100 nan 0.0100 0.0000
## 180 0.0088 nan 0.0100 0.0000
## 200 0.0078 nan 0.0100 -0.0000
##
## - Fold13: shrinkage=0.01, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold13: shrinkage=0.01, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0435 nan 0.0100 0.0005
## 2 0.0428 nan 0.0100 0.0006
## 3 0.0420 nan 0.0100 0.0006
## 4 0.0415 nan 0.0100 0.0002
## 5 0.0410 nan 0.0100 0.0002
## 6 0.0404 nan 0.0100 0.0005
## 7 0.0399 nan 0.0100 0.0004
## 8 0.0392 nan 0.0100 0.0006
## 9 0.0384 nan 0.0100 0.0007
## 10 0.0381 nan 0.0100 0.0002
## 20 0.0329 nan 0.0100 0.0004
## 40 0.0246 nan 0.0100 0.0004
## 60 0.0188 nan 0.0100 0.0001
## 80 0.0143 nan 0.0100 0.0001
## 100 0.0110 nan 0.0100 0.0001
## 120 0.0085 nan 0.0100 0.0001
## 140 0.0065 nan 0.0100 0.0000
## 160 0.0053 nan 0.0100 0.0001
## 180 0.0041 nan 0.0100 0.0000
## 200 0.0034 nan 0.0100 0.0000
##
## - Fold13: shrinkage=0.01, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold13: shrinkage=0.01, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0438 nan 0.0100 0.0002
## 2 0.0432 nan 0.0100 0.0006
## 3 0.0424 nan 0.0100 0.0007
## 4 0.0419 nan 0.0100 0.0006
## 5 0.0413 nan 0.0100 0.0006
## 6 0.0406 nan 0.0100 0.0005
## 7 0.0402 nan 0.0100 0.0002
## 8 0.0396 nan 0.0100 0.0004
## 9 0.0390 nan 0.0100 0.0005
## 10 0.0384 nan 0.0100 0.0003
## 20 0.0327 nan 0.0100 0.0005
## 40 0.0244 nan 0.0100 0.0001
## 60 0.0190 nan 0.0100 0.0001
## 80 0.0148 nan 0.0100 0.0001
## 100 0.0116 nan 0.0100 0.0000
## 120 0.0089 nan 0.0100 0.0001
## 140 0.0070 nan 0.0100 0.0000
## 160 0.0057 nan 0.0100 0.0000
## 180 0.0047 nan 0.0100 -0.0000
## 200 0.0038 nan 0.0100 0.0001
##
## - Fold13: shrinkage=0.01, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold13: shrinkage=0.01, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0440 nan 0.0100 0.0005
## 2 0.0434 nan 0.0100 0.0006
## 3 0.0430 nan 0.0100 0.0001
## 4 0.0427 nan 0.0100 -0.0002
## 5 0.0421 nan 0.0100 0.0005
## 6 0.0418 nan 0.0100 0.0003
## 7 0.0412 nan 0.0100 0.0006
## 8 0.0406 nan 0.0100 0.0006
## 9 0.0401 nan 0.0100 0.0005
## 10 0.0394 nan 0.0100 0.0006
## 20 0.0353 nan 0.0100 0.0001
## 40 0.0285 nan 0.0100 0.0004
## 60 0.0237 nan 0.0100 0.0003
## 80 0.0193 nan 0.0100 0.0002
## 100 0.0162 nan 0.0100 0.0001
## 120 0.0138 nan 0.0100 0.0001
## 140 0.0121 nan 0.0100 0.0001
## 160 0.0108 nan 0.0100 0.0000
## 180 0.0095 nan 0.0100 0.0000
## 200 0.0084 nan 0.0100 0.0000
##
## - Fold13: shrinkage=0.01, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold13: shrinkage=0.05, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0419 nan 0.0500 0.0026
## 2 0.0390 nan 0.0500 0.0027
## 3 0.0369 nan 0.0500 0.0016
## 4 0.0341 nan 0.0500 0.0020
## 5 0.0319 nan 0.0500 0.0019
## 6 0.0299 nan 0.0500 0.0018
## 7 0.0277 nan 0.0500 0.0014
## 8 0.0270 nan 0.0500 0.0003
## 9 0.0254 nan 0.0500 0.0013
## 10 0.0245 nan 0.0500 -0.0003
## 20 0.0149 nan 0.0500 0.0006
## 40 0.0065 nan 0.0500 0.0001
## 60 0.0028 nan 0.0500 0.0000
## 80 0.0015 nan 0.0500 -0.0000
## 100 0.0008 nan 0.0500 -0.0000
## 120 0.0004 nan 0.0500 -0.0000
## 140 0.0003 nan 0.0500 0.0000
## 160 0.0002 nan 0.0500 -0.0000
## 180 0.0001 nan 0.0500 -0.0000
## 200 0.0001 nan 0.0500 0.0000
##
## - Fold13: shrinkage=0.05, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold13: shrinkage=0.05, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0416 nan 0.0500 0.0028
## 2 0.0411 nan 0.0500 -0.0013
## 3 0.0389 nan 0.0500 0.0023
## 4 0.0364 nan 0.0500 0.0016
## 5 0.0352 nan 0.0500 0.0007
## 6 0.0334 nan 0.0500 -0.0000
## 7 0.0312 nan 0.0500 0.0022
## 8 0.0299 nan 0.0500 -0.0002
## 9 0.0274 nan 0.0500 0.0018
## 10 0.0266 nan 0.0500 0.0001
## 20 0.0153 nan 0.0500 0.0009
## 40 0.0060 nan 0.0500 0.0002
## 60 0.0033 nan 0.0500 0.0001
## 80 0.0019 nan 0.0500 -0.0000
## 100 0.0011 nan 0.0500 -0.0000
## 120 0.0006 nan 0.0500 -0.0000
## 140 0.0004 nan 0.0500 -0.0000
## 160 0.0003 nan 0.0500 -0.0000
## 180 0.0002 nan 0.0500 0.0000
## 200 0.0001 nan 0.0500 -0.0000
##
## - Fold13: shrinkage=0.05, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold13: shrinkage=0.05, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0416 nan 0.0500 0.0024
## 2 0.0389 nan 0.0500 0.0021
## 3 0.0367 nan 0.0500 0.0022
## 4 0.0346 nan 0.0500 0.0021
## 5 0.0328 nan 0.0500 0.0010
## 6 0.0308 nan 0.0500 0.0010
## 7 0.0297 nan 0.0500 0.0009
## 8 0.0285 nan 0.0500 0.0007
## 9 0.0270 nan 0.0500 0.0008
## 10 0.0254 nan 0.0500 0.0015
## 20 0.0158 nan 0.0500 0.0002
## 40 0.0080 nan 0.0500 0.0002
## 60 0.0047 nan 0.0500 0.0000
## 80 0.0028 nan 0.0500 0.0000
## 100 0.0020 nan 0.0500 0.0000
## 120 0.0014 nan 0.0500 -0.0000
## 140 0.0010 nan 0.0500 0.0000
## 160 0.0007 nan 0.0500 0.0000
## 180 0.0006 nan 0.0500 -0.0000
## 200 0.0004 nan 0.0500 -0.0000
##
## - Fold13: shrinkage=0.05, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold13: shrinkage=0.05, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0411 nan 0.0500 0.0031
## 2 0.0392 nan 0.0500 0.0020
## 3 0.0366 nan 0.0500 0.0018
## 4 0.0336 nan 0.0500 0.0024
## 5 0.0315 nan 0.0500 0.0008
## 6 0.0299 nan 0.0500 0.0007
## 7 0.0282 nan 0.0500 0.0013
## 8 0.0265 nan 0.0500 0.0005
## 9 0.0245 nan 0.0500 0.0019
## 10 0.0228 nan 0.0500 0.0018
## 20 0.0119 nan 0.0500 -0.0002
## 40 0.0045 nan 0.0500 -0.0001
## 60 0.0015 nan 0.0500 -0.0001
## 80 0.0006 nan 0.0500 -0.0000
## 100 0.0003 nan 0.0500 -0.0000
## 120 0.0001 nan 0.0500 -0.0000
## 140 0.0001 nan 0.0500 -0.0000
## 160 0.0000 nan 0.0500 -0.0000
## 180 0.0000 nan 0.0500 -0.0000
## 200 0.0000 nan 0.0500 0.0000
##
## - Fold13: shrinkage=0.05, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold13: shrinkage=0.05, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0411 nan 0.0500 0.0032
## 2 0.0383 nan 0.0500 0.0021
## 3 0.0355 nan 0.0500 0.0029
## 4 0.0327 nan 0.0500 0.0029
## 5 0.0310 nan 0.0500 0.0019
## 6 0.0289 nan 0.0500 0.0017
## 7 0.0269 nan 0.0500 0.0018
## 8 0.0255 nan 0.0500 0.0016
## 9 0.0234 nan 0.0500 0.0016
## 10 0.0214 nan 0.0500 0.0019
## 20 0.0123 nan 0.0500 0.0003
## 40 0.0045 nan 0.0500 -0.0000
## 60 0.0023 nan 0.0500 0.0000
## 80 0.0012 nan 0.0500 0.0000
## 100 0.0007 nan 0.0500 -0.0000
## 120 0.0004 nan 0.0500 -0.0000
## 140 0.0003 nan 0.0500 -0.0000
## 160 0.0002 nan 0.0500 -0.0000
## 180 0.0001 nan 0.0500 -0.0000
## 200 0.0001 nan 0.0500 -0.0000
##
## - Fold13: shrinkage=0.05, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold13: shrinkage=0.05, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0409 nan 0.0500 0.0026
## 2 0.0385 nan 0.0500 0.0013
## 3 0.0364 nan 0.0500 0.0013
## 4 0.0340 nan 0.0500 0.0024
## 5 0.0319 nan 0.0500 0.0019
## 6 0.0301 nan 0.0500 0.0017
## 7 0.0285 nan 0.0500 0.0018
## 8 0.0267 nan 0.0500 0.0013
## 9 0.0248 nan 0.0500 0.0017
## 10 0.0233 nan 0.0500 0.0015
## 20 0.0145 nan 0.0500 0.0004
## 40 0.0075 nan 0.0500 -0.0000
## 60 0.0040 nan 0.0500 -0.0001
## 80 0.0027 nan 0.0500 -0.0000
## 100 0.0019 nan 0.0500 -0.0000
## 120 0.0013 nan 0.0500 0.0000
## 140 0.0009 nan 0.0500 0.0000
## 160 0.0007 nan 0.0500 -0.0000
## 180 0.0004 nan 0.0500 -0.0000
## 200 0.0003 nan 0.0500 -0.0000
##
## - Fold13: shrinkage=0.05, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold13: shrinkage=0.05, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0415 nan 0.0500 0.0030
## 2 0.0376 nan 0.0500 0.0040
## 3 0.0354 nan 0.0500 0.0023
## 4 0.0325 nan 0.0500 0.0018
## 5 0.0301 nan 0.0500 0.0024
## 6 0.0287 nan 0.0500 0.0011
## 7 0.0264 nan 0.0500 0.0011
## 8 0.0240 nan 0.0500 0.0023
## 9 0.0231 nan 0.0500 0.0008
## 10 0.0221 nan 0.0500 0.0010
## 20 0.0124 nan 0.0500 0.0004
## 40 0.0037 nan 0.0500 0.0001
## 60 0.0013 nan 0.0500 0.0000
## 80 0.0004 nan 0.0500 -0.0000
## 100 0.0002 nan 0.0500 -0.0000
## 120 0.0001 nan 0.0500 0.0000
## 140 0.0000 nan 0.0500 -0.0000
## 160 0.0000 nan 0.0500 -0.0000
## 180 0.0000 nan 0.0500 -0.0000
## 200 0.0000 nan 0.0500 -0.0000
##
## - Fold13: shrinkage=0.05, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold13: shrinkage=0.05, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0424 nan 0.0500 0.0020
## 2 0.0389 nan 0.0500 0.0034
## 3 0.0359 nan 0.0500 0.0028
## 4 0.0332 nan 0.0500 0.0024
## 5 0.0296 nan 0.0500 0.0027
## 6 0.0278 nan 0.0500 0.0016
## 7 0.0258 nan 0.0500 0.0005
## 8 0.0242 nan 0.0500 0.0018
## 9 0.0226 nan 0.0500 0.0016
## 10 0.0216 nan 0.0500 0.0004
## 20 0.0108 nan 0.0500 0.0005
## 40 0.0041 nan 0.0500 0.0001
## 60 0.0019 nan 0.0500 0.0000
## 80 0.0011 nan 0.0500 0.0000
## 100 0.0008 nan 0.0500 0.0000
## 120 0.0006 nan 0.0500 -0.0000
## 140 0.0004 nan 0.0500 -0.0000
## 160 0.0002 nan 0.0500 -0.0000
## 180 0.0002 nan 0.0500 -0.0000
## 200 0.0001 nan 0.0500 -0.0000
##
## - Fold13: shrinkage=0.05, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold13: shrinkage=0.05, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0425 nan 0.0500 0.0003
## 2 0.0395 nan 0.0500 0.0027
## 3 0.0371 nan 0.0500 0.0018
## 4 0.0346 nan 0.0500 0.0024
## 5 0.0329 nan 0.0500 0.0008
## 6 0.0318 nan 0.0500 -0.0001
## 7 0.0300 nan 0.0500 0.0004
## 8 0.0278 nan 0.0500 0.0016
## 9 0.0262 nan 0.0500 0.0015
## 10 0.0248 nan 0.0500 0.0007
## 20 0.0162 nan 0.0500 0.0002
## 40 0.0077 nan 0.0500 0.0002
## 60 0.0044 nan 0.0500 0.0000
## 80 0.0029 nan 0.0500 -0.0001
## 100 0.0020 nan 0.0500 -0.0001
## 120 0.0014 nan 0.0500 0.0000
## 140 0.0010 nan 0.0500 0.0000
## 160 0.0006 nan 0.0500 -0.0000
## 180 0.0004 nan 0.0500 0.0000
## 200 0.0003 nan 0.0500 -0.0000
##
## - Fold13: shrinkage=0.05, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold13: shrinkage=0.10, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0397 nan 0.1000 0.0035
## 2 0.0348 nan 0.1000 0.0048
## 3 0.0309 nan 0.1000 0.0044
## 4 0.0287 nan 0.1000 0.0023
## 5 0.0253 nan 0.1000 0.0031
## 6 0.0223 nan 0.1000 0.0027
## 7 0.0208 nan 0.1000 0.0009
## 8 0.0184 nan 0.1000 0.0014
## 9 0.0174 nan 0.1000 0.0003
## 10 0.0159 nan 0.1000 0.0008
## 20 0.0064 nan 0.1000 0.0002
## 40 0.0017 nan 0.1000 -0.0000
## 60 0.0006 nan 0.1000 0.0000
## 80 0.0003 nan 0.1000 0.0000
## 100 0.0001 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold13: shrinkage=0.10, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold13: shrinkage=0.10, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0387 nan 0.1000 0.0052
## 2 0.0332 nan 0.1000 0.0048
## 3 0.0297 nan 0.1000 0.0030
## 4 0.0265 nan 0.1000 0.0035
## 5 0.0256 nan 0.1000 -0.0003
## 6 0.0229 nan 0.1000 0.0011
## 7 0.0198 nan 0.1000 0.0010
## 8 0.0180 nan 0.1000 0.0021
## 9 0.0160 nan 0.1000 0.0014
## 10 0.0151 nan 0.1000 0.0004
## 20 0.0083 nan 0.1000 0.0005
## 40 0.0025 nan 0.1000 -0.0001
## 60 0.0010 nan 0.1000 -0.0001
## 80 0.0004 nan 0.1000 -0.0000
## 100 0.0001 nan 0.1000 -0.0000
## 120 0.0001 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold13: shrinkage=0.10, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold13: shrinkage=0.10, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0384 nan 0.1000 0.0061
## 2 0.0332 nan 0.1000 0.0029
## 3 0.0300 nan 0.1000 0.0030
## 4 0.0272 nan 0.1000 -0.0002
## 5 0.0238 nan 0.1000 0.0027
## 6 0.0220 nan 0.1000 0.0015
## 7 0.0200 nan 0.1000 0.0021
## 8 0.0173 nan 0.1000 0.0019
## 9 0.0153 nan 0.1000 0.0009
## 10 0.0132 nan 0.1000 0.0012
## 20 0.0076 nan 0.1000 -0.0002
## 40 0.0026 nan 0.1000 0.0000
## 60 0.0012 nan 0.1000 -0.0000
## 80 0.0008 nan 0.1000 -0.0000
## 100 0.0004 nan 0.1000 -0.0000
## 120 0.0002 nan 0.1000 -0.0000
## 140 0.0001 nan 0.1000 -0.0000
## 160 0.0001 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold13: shrinkage=0.10, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold13: shrinkage=0.10, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0373 nan 0.1000 0.0077
## 2 0.0315 nan 0.1000 0.0049
## 3 0.0267 nan 0.1000 0.0054
## 4 0.0260 nan 0.1000 -0.0017
## 5 0.0222 nan 0.1000 0.0028
## 6 0.0189 nan 0.1000 0.0026
## 7 0.0165 nan 0.1000 0.0013
## 8 0.0144 nan 0.1000 0.0020
## 9 0.0127 nan 0.1000 0.0014
## 10 0.0108 nan 0.1000 0.0010
## 20 0.0042 nan 0.1000 -0.0001
## 40 0.0006 nan 0.1000 0.0000
## 60 0.0002 nan 0.1000 -0.0000
## 80 0.0001 nan 0.1000 -0.0000
## 100 0.0000 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold13: shrinkage=0.10, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold13: shrinkage=0.10, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0393 nan 0.1000 0.0022
## 2 0.0361 nan 0.1000 0.0015
## 3 0.0303 nan 0.1000 0.0047
## 4 0.0246 nan 0.1000 0.0036
## 5 0.0211 nan 0.1000 0.0035
## 6 0.0184 nan 0.1000 0.0015
## 7 0.0168 nan 0.1000 0.0017
## 8 0.0141 nan 0.1000 0.0019
## 9 0.0123 nan 0.1000 0.0016
## 10 0.0109 nan 0.1000 0.0001
## 20 0.0041 nan 0.1000 0.0002
## 40 0.0009 nan 0.1000 0.0001
## 60 0.0003 nan 0.1000 -0.0000
## 80 0.0001 nan 0.1000 0.0000
## 100 0.0001 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold13: shrinkage=0.10, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold13: shrinkage=0.10, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0389 nan 0.1000 0.0037
## 2 0.0333 nan 0.1000 0.0054
## 3 0.0277 nan 0.1000 0.0038
## 4 0.0251 nan 0.1000 0.0030
## 5 0.0230 nan 0.1000 0.0019
## 6 0.0204 nan 0.1000 0.0018
## 7 0.0186 nan 0.1000 -0.0008
## 8 0.0171 nan 0.1000 0.0016
## 9 0.0162 nan 0.1000 0.0003
## 10 0.0150 nan 0.1000 0.0014
## 20 0.0072 nan 0.1000 0.0002
## 40 0.0029 nan 0.1000 -0.0000
## 60 0.0014 nan 0.1000 -0.0000
## 80 0.0007 nan 0.1000 -0.0000
## 100 0.0004 nan 0.1000 -0.0000
## 120 0.0002 nan 0.1000 -0.0000
## 140 0.0001 nan 0.1000 -0.0000
## 160 0.0001 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold13: shrinkage=0.10, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold13: shrinkage=0.10, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0362 nan 0.1000 0.0078
## 2 0.0313 nan 0.1000 0.0045
## 3 0.0260 nan 0.1000 0.0052
## 4 0.0225 nan 0.1000 0.0028
## 5 0.0193 nan 0.1000 0.0018
## 6 0.0173 nan 0.1000 0.0009
## 7 0.0152 nan 0.1000 0.0013
## 8 0.0134 nan 0.1000 0.0008
## 9 0.0111 nan 0.1000 0.0016
## 10 0.0102 nan 0.1000 0.0001
## 20 0.0037 nan 0.1000 -0.0000
## 40 0.0004 nan 0.1000 -0.0000
## 60 0.0001 nan 0.1000 -0.0000
## 80 0.0000 nan 0.1000 -0.0000
## 100 0.0000 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold13: shrinkage=0.10, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold13: shrinkage=0.10, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0388 nan 0.1000 0.0038
## 2 0.0343 nan 0.1000 0.0043
## 3 0.0291 nan 0.1000 0.0046
## 4 0.0264 nan 0.1000 0.0010
## 5 0.0240 nan 0.1000 0.0004
## 6 0.0195 nan 0.1000 0.0029
## 7 0.0170 nan 0.1000 -0.0002
## 8 0.0155 nan 0.1000 0.0010
## 9 0.0137 nan 0.1000 0.0012
## 10 0.0122 nan 0.1000 0.0011
## 20 0.0041 nan 0.1000 0.0003
## 40 0.0012 nan 0.1000 -0.0001
## 60 0.0003 nan 0.1000 -0.0000
## 80 0.0001 nan 0.1000 -0.0000
## 100 0.0000 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold13: shrinkage=0.10, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold13: shrinkage=0.10, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0384 nan 0.1000 0.0053
## 2 0.0339 nan 0.1000 0.0044
## 3 0.0304 nan 0.1000 0.0013
## 4 0.0280 nan 0.1000 0.0018
## 5 0.0258 nan 0.1000 0.0026
## 6 0.0232 nan 0.1000 0.0029
## 7 0.0207 nan 0.1000 0.0023
## 8 0.0187 nan 0.1000 0.0010
## 9 0.0172 nan 0.1000 0.0016
## 10 0.0159 nan 0.1000 0.0012
## 20 0.0076 nan 0.1000 0.0000
## 40 0.0027 nan 0.1000 0.0000
## 60 0.0013 nan 0.1000 -0.0001
## 80 0.0007 nan 0.1000 0.0000
## 100 0.0004 nan 0.1000 0.0000
## 120 0.0002 nan 0.1000 -0.0000
## 140 0.0001 nan 0.1000 -0.0000
## 160 0.0001 nan 0.1000 -0.0000
## 180 0.0001 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold13: shrinkage=0.10, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold14: shrinkage=0.01, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0432 nan 0.0100 0.0002
## 2 0.0426 nan 0.0100 0.0001
## 3 0.0423 nan 0.0100 0.0002
## 4 0.0419 nan 0.0100 0.0001
## 5 0.0415 nan 0.0100 0.0002
## 6 0.0409 nan 0.0100 0.0005
## 7 0.0405 nan 0.0100 0.0004
## 8 0.0399 nan 0.0100 0.0006
## 9 0.0395 nan 0.0100 0.0004
## 10 0.0388 nan 0.0100 0.0004
## 20 0.0345 nan 0.0100 0.0003
## 40 0.0271 nan 0.0100 0.0003
## 60 0.0222 nan 0.0100 0.0003
## 80 0.0179 nan 0.0100 0.0002
## 100 0.0147 nan 0.0100 0.0000
## 120 0.0120 nan 0.0100 0.0001
## 140 0.0098 nan 0.0100 0.0000
## 160 0.0084 nan 0.0100 0.0000
## 180 0.0069 nan 0.0100 -0.0000
## 200 0.0057 nan 0.0100 0.0000
##
## - Fold14: shrinkage=0.01, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold14: shrinkage=0.01, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0431 nan 0.0100 0.0002
## 2 0.0427 nan 0.0100 0.0004
## 3 0.0422 nan 0.0100 0.0002
## 4 0.0417 nan 0.0100 0.0005
## 5 0.0414 nan 0.0100 0.0003
## 6 0.0407 nan 0.0100 0.0004
## 7 0.0402 nan 0.0100 0.0005
## 8 0.0397 nan 0.0100 0.0005
## 9 0.0391 nan 0.0100 0.0004
## 10 0.0386 nan 0.0100 0.0003
## 20 0.0342 nan 0.0100 0.0004
## 40 0.0274 nan 0.0100 0.0003
## 60 0.0217 nan 0.0100 0.0002
## 80 0.0177 nan 0.0100 0.0000
## 100 0.0149 nan 0.0100 0.0001
## 120 0.0124 nan 0.0100 0.0001
## 140 0.0106 nan 0.0100 0.0000
## 160 0.0091 nan 0.0100 -0.0000
## 180 0.0077 nan 0.0100 0.0001
## 200 0.0067 nan 0.0100 0.0000
##
## - Fold14: shrinkage=0.01, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold14: shrinkage=0.01, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0429 nan 0.0100 0.0006
## 2 0.0424 nan 0.0100 0.0005
## 3 0.0423 nan 0.0100 -0.0000
## 4 0.0417 nan 0.0100 0.0003
## 5 0.0413 nan 0.0100 0.0005
## 6 0.0406 nan 0.0100 0.0006
## 7 0.0401 nan 0.0100 0.0003
## 8 0.0396 nan 0.0100 0.0005
## 9 0.0392 nan 0.0100 0.0005
## 10 0.0387 nan 0.0100 0.0005
## 20 0.0348 nan 0.0100 0.0004
## 40 0.0270 nan 0.0100 0.0003
## 60 0.0220 nan 0.0100 0.0002
## 80 0.0185 nan 0.0100 0.0001
## 100 0.0157 nan 0.0100 -0.0000
## 120 0.0137 nan 0.0100 -0.0000
## 140 0.0117 nan 0.0100 0.0001
## 160 0.0103 nan 0.0100 -0.0000
## 180 0.0091 nan 0.0100 0.0001
## 200 0.0082 nan 0.0100 0.0000
##
## - Fold14: shrinkage=0.01, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold14: shrinkage=0.01, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0428 nan 0.0100 0.0007
## 2 0.0422 nan 0.0100 0.0005
## 3 0.0417 nan 0.0100 -0.0001
## 4 0.0411 nan 0.0100 0.0008
## 5 0.0404 nan 0.0100 0.0006
## 6 0.0398 nan 0.0100 0.0004
## 7 0.0391 nan 0.0100 0.0006
## 8 0.0388 nan 0.0100 0.0002
## 9 0.0384 nan 0.0100 0.0004
## 10 0.0380 nan 0.0100 0.0002
## 20 0.0332 nan 0.0100 0.0004
## 40 0.0248 nan 0.0100 0.0002
## 60 0.0187 nan 0.0100 0.0001
## 80 0.0147 nan 0.0100 0.0001
## 100 0.0113 nan 0.0100 0.0001
## 120 0.0090 nan 0.0100 0.0000
## 140 0.0071 nan 0.0100 0.0001
## 160 0.0056 nan 0.0100 0.0000
## 180 0.0044 nan 0.0100 0.0001
## 200 0.0036 nan 0.0100 0.0000
##
## - Fold14: shrinkage=0.01, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold14: shrinkage=0.01, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0433 nan 0.0100 0.0002
## 2 0.0427 nan 0.0100 0.0005
## 3 0.0424 nan 0.0100 0.0003
## 4 0.0420 nan 0.0100 0.0004
## 5 0.0417 nan 0.0100 -0.0000
## 6 0.0412 nan 0.0100 0.0004
## 7 0.0407 nan 0.0100 0.0004
## 8 0.0401 nan 0.0100 0.0007
## 9 0.0394 nan 0.0100 0.0004
## 10 0.0388 nan 0.0100 0.0004
## 20 0.0338 nan 0.0100 0.0001
## 40 0.0259 nan 0.0100 0.0003
## 60 0.0201 nan 0.0100 0.0002
## 80 0.0157 nan 0.0100 0.0002
## 100 0.0122 nan 0.0100 0.0001
## 120 0.0100 nan 0.0100 0.0001
## 140 0.0081 nan 0.0100 0.0001
## 160 0.0065 nan 0.0100 0.0000
## 180 0.0055 nan 0.0100 0.0000
## 200 0.0045 nan 0.0100 0.0000
##
## - Fold14: shrinkage=0.01, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold14: shrinkage=0.01, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0434 nan 0.0100 0.0001
## 2 0.0429 nan 0.0100 0.0003
## 3 0.0425 nan 0.0100 0.0003
## 4 0.0420 nan 0.0100 0.0005
## 5 0.0414 nan 0.0100 0.0005
## 6 0.0410 nan 0.0100 0.0004
## 7 0.0407 nan 0.0100 0.0001
## 8 0.0403 nan 0.0100 0.0001
## 9 0.0399 nan 0.0100 0.0004
## 10 0.0393 nan 0.0100 0.0005
## 20 0.0348 nan 0.0100 0.0004
## 40 0.0276 nan 0.0100 0.0003
## 60 0.0224 nan 0.0100 0.0003
## 80 0.0186 nan 0.0100 0.0001
## 100 0.0153 nan 0.0100 0.0001
## 120 0.0132 nan 0.0100 -0.0001
## 140 0.0114 nan 0.0100 0.0001
## 160 0.0099 nan 0.0100 0.0000
## 180 0.0088 nan 0.0100 0.0000
## 200 0.0077 nan 0.0100 0.0000
##
## - Fold14: shrinkage=0.01, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold14: shrinkage=0.01, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0429 nan 0.0100 0.0005
## 2 0.0424 nan 0.0100 0.0004
## 3 0.0417 nan 0.0100 0.0004
## 4 0.0410 nan 0.0100 0.0005
## 5 0.0407 nan 0.0100 0.0002
## 6 0.0402 nan 0.0100 0.0002
## 7 0.0396 nan 0.0100 0.0004
## 8 0.0391 nan 0.0100 0.0004
## 9 0.0385 nan 0.0100 0.0005
## 10 0.0377 nan 0.0100 0.0006
## 20 0.0324 nan 0.0100 0.0004
## 40 0.0241 nan 0.0100 0.0002
## 60 0.0183 nan 0.0100 0.0002
## 80 0.0143 nan 0.0100 0.0000
## 100 0.0109 nan 0.0100 0.0001
## 120 0.0083 nan 0.0100 0.0001
## 140 0.0065 nan 0.0100 0.0001
## 160 0.0053 nan 0.0100 0.0000
## 180 0.0043 nan 0.0100 0.0000
## 200 0.0036 nan 0.0100 0.0000
##
## - Fold14: shrinkage=0.01, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold14: shrinkage=0.01, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0431 nan 0.0100 0.0005
## 2 0.0425 nan 0.0100 0.0005
## 3 0.0419 nan 0.0100 0.0004
## 4 0.0412 nan 0.0100 0.0005
## 5 0.0408 nan 0.0100 0.0002
## 6 0.0405 nan 0.0100 0.0003
## 7 0.0400 nan 0.0100 0.0004
## 8 0.0395 nan 0.0100 0.0004
## 9 0.0388 nan 0.0100 0.0004
## 10 0.0384 nan 0.0100 0.0005
## 20 0.0337 nan 0.0100 0.0002
## 40 0.0259 nan 0.0100 0.0002
## 60 0.0199 nan 0.0100 0.0002
## 80 0.0152 nan 0.0100 0.0001
## 100 0.0120 nan 0.0100 0.0001
## 120 0.0096 nan 0.0100 0.0000
## 140 0.0077 nan 0.0100 -0.0001
## 160 0.0061 nan 0.0100 0.0000
## 180 0.0050 nan 0.0100 0.0000
## 200 0.0041 nan 0.0100 0.0000
##
## - Fold14: shrinkage=0.01, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold14: shrinkage=0.01, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0433 nan 0.0100 0.0004
## 2 0.0428 nan 0.0100 0.0005
## 3 0.0423 nan 0.0100 0.0006
## 4 0.0418 nan 0.0100 0.0005
## 5 0.0415 nan 0.0100 0.0001
## 6 0.0411 nan 0.0100 0.0005
## 7 0.0407 nan 0.0100 0.0003
## 8 0.0402 nan 0.0100 0.0003
## 9 0.0398 nan 0.0100 0.0001
## 10 0.0391 nan 0.0100 0.0005
## 20 0.0348 nan 0.0100 0.0005
## 40 0.0282 nan 0.0100 -0.0001
## 60 0.0230 nan 0.0100 0.0003
## 80 0.0193 nan 0.0100 0.0001
## 100 0.0160 nan 0.0100 0.0000
## 120 0.0134 nan 0.0100 0.0001
## 140 0.0111 nan 0.0100 0.0001
## 160 0.0097 nan 0.0100 0.0001
## 180 0.0086 nan 0.0100 0.0000
## 200 0.0077 nan 0.0100 0.0000
##
## - Fold14: shrinkage=0.01, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold14: shrinkage=0.05, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0407 nan 0.0500 0.0026
## 2 0.0383 nan 0.0500 0.0022
## 3 0.0359 nan 0.0500 0.0028
## 4 0.0342 nan 0.0500 0.0014
## 5 0.0313 nan 0.0500 0.0030
## 6 0.0306 nan 0.0500 -0.0004
## 7 0.0290 nan 0.0500 0.0018
## 8 0.0268 nan 0.0500 0.0013
## 9 0.0251 nan 0.0500 0.0017
## 10 0.0244 nan 0.0500 0.0008
## 20 0.0145 nan 0.0500 0.0007
## 40 0.0065 nan 0.0500 0.0000
## 60 0.0032 nan 0.0500 0.0001
## 80 0.0016 nan 0.0500 0.0000
## 100 0.0008 nan 0.0500 0.0000
## 120 0.0005 nan 0.0500 -0.0000
## 140 0.0003 nan 0.0500 0.0000
## 160 0.0002 nan 0.0500 -0.0000
## 180 0.0001 nan 0.0500 -0.0000
## 200 0.0001 nan 0.0500 -0.0000
##
## - Fold14: shrinkage=0.05, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold14: shrinkage=0.05, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0417 nan 0.0500 0.0016
## 2 0.0392 nan 0.0500 0.0009
## 3 0.0377 nan 0.0500 0.0013
## 4 0.0348 nan 0.0500 0.0025
## 5 0.0330 nan 0.0500 0.0022
## 6 0.0310 nan 0.0500 0.0021
## 7 0.0286 nan 0.0500 0.0019
## 8 0.0271 nan 0.0500 0.0001
## 9 0.0256 nan 0.0500 0.0014
## 10 0.0246 nan 0.0500 0.0001
## 20 0.0138 nan 0.0500 0.0009
## 40 0.0060 nan 0.0500 0.0002
## 60 0.0029 nan 0.0500 -0.0000
## 80 0.0016 nan 0.0500 -0.0000
## 100 0.0010 nan 0.0500 -0.0000
## 120 0.0007 nan 0.0500 0.0000
## 140 0.0004 nan 0.0500 -0.0000
## 160 0.0003 nan 0.0500 0.0000
## 180 0.0002 nan 0.0500 -0.0000
## 200 0.0001 nan 0.0500 0.0000
##
## - Fold14: shrinkage=0.05, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold14: shrinkage=0.05, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0409 nan 0.0500 0.0030
## 2 0.0381 nan 0.0500 0.0028
## 3 0.0356 nan 0.0500 0.0023
## 4 0.0349 nan 0.0500 -0.0003
## 5 0.0331 nan 0.0500 0.0019
## 6 0.0316 nan 0.0500 0.0011
## 7 0.0303 nan 0.0500 0.0012
## 8 0.0285 nan 0.0500 0.0015
## 9 0.0276 nan 0.0500 0.0011
## 10 0.0261 nan 0.0500 0.0013
## 20 0.0171 nan 0.0500 0.0007
## 40 0.0078 nan 0.0500 0.0002
## 60 0.0047 nan 0.0500 0.0001
## 80 0.0031 nan 0.0500 0.0000
## 100 0.0021 nan 0.0500 -0.0000
## 120 0.0014 nan 0.0500 -0.0000
## 140 0.0009 nan 0.0500 -0.0000
## 160 0.0006 nan 0.0500 -0.0000
## 180 0.0005 nan 0.0500 0.0000
## 200 0.0003 nan 0.0500 0.0000
##
## - Fold14: shrinkage=0.05, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold14: shrinkage=0.05, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0403 nan 0.0500 0.0035
## 2 0.0375 nan 0.0500 0.0015
## 3 0.0352 nan 0.0500 0.0014
## 4 0.0327 nan 0.0500 0.0025
## 5 0.0304 nan 0.0500 0.0017
## 6 0.0278 nan 0.0500 0.0017
## 7 0.0265 nan 0.0500 0.0012
## 8 0.0256 nan 0.0500 0.0001
## 9 0.0238 nan 0.0500 0.0005
## 10 0.0234 nan 0.0500 0.0000
## 20 0.0121 nan 0.0500 0.0008
## 40 0.0033 nan 0.0500 0.0001
## 60 0.0013 nan 0.0500 0.0001
## 80 0.0007 nan 0.0500 0.0000
## 100 0.0003 nan 0.0500 -0.0000
## 120 0.0001 nan 0.0500 -0.0000
## 140 0.0001 nan 0.0500 -0.0000
## 160 0.0000 nan 0.0500 -0.0000
## 180 0.0000 nan 0.0500 0.0000
## 200 0.0000 nan 0.0500 -0.0000
##
## - Fold14: shrinkage=0.05, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold14: shrinkage=0.05, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0412 nan 0.0500 0.0026
## 2 0.0382 nan 0.0500 0.0028
## 3 0.0358 nan 0.0500 0.0014
## 4 0.0333 nan 0.0500 0.0015
## 5 0.0313 nan 0.0500 0.0009
## 6 0.0289 nan 0.0500 0.0023
## 7 0.0266 nan 0.0500 0.0013
## 8 0.0250 nan 0.0500 0.0009
## 9 0.0228 nan 0.0500 0.0016
## 10 0.0214 nan 0.0500 0.0008
## 20 0.0122 nan 0.0500 0.0009
## 40 0.0046 nan 0.0500 0.0001
## 60 0.0019 nan 0.0500 0.0000
## 80 0.0010 nan 0.0500 0.0000
## 100 0.0006 nan 0.0500 -0.0000
## 120 0.0003 nan 0.0500 -0.0000
## 140 0.0002 nan 0.0500 -0.0000
## 160 0.0001 nan 0.0500 -0.0000
## 180 0.0001 nan 0.0500 -0.0000
## 200 0.0001 nan 0.0500 -0.0000
##
## - Fold14: shrinkage=0.05, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold14: shrinkage=0.05, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0411 nan 0.0500 0.0023
## 2 0.0391 nan 0.0500 0.0018
## 3 0.0367 nan 0.0500 0.0008
## 4 0.0347 nan 0.0500 0.0007
## 5 0.0325 nan 0.0500 0.0009
## 6 0.0304 nan 0.0500 0.0015
## 7 0.0284 nan 0.0500 0.0015
## 8 0.0270 nan 0.0500 0.0007
## 9 0.0253 nan 0.0500 0.0011
## 10 0.0242 nan 0.0500 0.0007
## 20 0.0159 nan 0.0500 0.0009
## 40 0.0085 nan 0.0500 -0.0001
## 60 0.0052 nan 0.0500 0.0001
## 80 0.0033 nan 0.0500 -0.0001
## 100 0.0025 nan 0.0500 -0.0001
## 120 0.0018 nan 0.0500 -0.0001
## 140 0.0013 nan 0.0500 -0.0000
## 160 0.0008 nan 0.0500 -0.0000
## 180 0.0005 nan 0.0500 -0.0000
## 200 0.0004 nan 0.0500 -0.0000
##
## - Fold14: shrinkage=0.05, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold14: shrinkage=0.05, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0412 nan 0.0500 0.0019
## 2 0.0388 nan 0.0500 0.0011
## 3 0.0354 nan 0.0500 0.0034
## 4 0.0337 nan 0.0500 0.0008
## 5 0.0325 nan 0.0500 -0.0004
## 6 0.0298 nan 0.0500 0.0021
## 7 0.0275 nan 0.0500 0.0020
## 8 0.0256 nan 0.0500 0.0017
## 9 0.0240 nan 0.0500 0.0015
## 10 0.0220 nan 0.0500 0.0019
## 20 0.0112 nan 0.0500 0.0002
## 40 0.0031 nan 0.0500 0.0000
## 60 0.0013 nan 0.0500 0.0000
## 80 0.0005 nan 0.0500 0.0000
## 100 0.0003 nan 0.0500 0.0000
## 120 0.0001 nan 0.0500 -0.0000
## 140 0.0001 nan 0.0500 -0.0000
## 160 0.0000 nan 0.0500 -0.0000
## 180 0.0000 nan 0.0500 -0.0000
## 200 0.0000 nan 0.0500 -0.0000
##
## - Fold14: shrinkage=0.05, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold14: shrinkage=0.05, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0424 nan 0.0500 -0.0001
## 2 0.0393 nan 0.0500 0.0017
## 3 0.0364 nan 0.0500 0.0022
## 4 0.0341 nan 0.0500 0.0019
## 5 0.0319 nan 0.0500 0.0015
## 6 0.0295 nan 0.0500 0.0020
## 7 0.0264 nan 0.0500 0.0019
## 8 0.0241 nan 0.0500 0.0016
## 9 0.0228 nan 0.0500 0.0016
## 10 0.0218 nan 0.0500 0.0009
## 20 0.0121 nan 0.0500 0.0004
## 40 0.0039 nan 0.0500 0.0001
## 60 0.0020 nan 0.0500 -0.0000
## 80 0.0010 nan 0.0500 0.0000
## 100 0.0005 nan 0.0500 -0.0000
## 120 0.0003 nan 0.0500 -0.0000
## 140 0.0002 nan 0.0500 0.0000
## 160 0.0001 nan 0.0500 -0.0000
## 180 0.0001 nan 0.0500 -0.0000
## 200 0.0001 nan 0.0500 -0.0000
##
## - Fold14: shrinkage=0.05, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold14: shrinkage=0.05, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0398 nan 0.0500 0.0020
## 2 0.0368 nan 0.0500 0.0016
## 3 0.0343 nan 0.0500 0.0020
## 4 0.0317 nan 0.0500 0.0021
## 5 0.0304 nan 0.0500 0.0002
## 6 0.0291 nan 0.0500 0.0014
## 7 0.0273 nan 0.0500 0.0010
## 8 0.0257 nan 0.0500 0.0015
## 9 0.0249 nan 0.0500 0.0002
## 10 0.0245 nan 0.0500 -0.0001
## 20 0.0161 nan 0.0500 0.0003
## 40 0.0084 nan 0.0500 -0.0000
## 60 0.0046 nan 0.0500 0.0001
## 80 0.0029 nan 0.0500 -0.0000
## 100 0.0021 nan 0.0500 -0.0001
## 120 0.0014 nan 0.0500 -0.0000
## 140 0.0011 nan 0.0500 0.0000
## 160 0.0008 nan 0.0500 -0.0000
## 180 0.0006 nan 0.0500 -0.0000
## 200 0.0004 nan 0.0500 -0.0000
##
## - Fold14: shrinkage=0.05, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold14: shrinkage=0.10, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0365 nan 0.1000 0.0049
## 2 0.0317 nan 0.1000 0.0043
## 3 0.0289 nan 0.1000 0.0029
## 4 0.0252 nan 0.1000 0.0024
## 5 0.0237 nan 0.1000 0.0015
## 6 0.0215 nan 0.1000 0.0022
## 7 0.0199 nan 0.1000 -0.0006
## 8 0.0171 nan 0.1000 0.0025
## 9 0.0156 nan 0.1000 0.0001
## 10 0.0143 nan 0.1000 0.0013
## 20 0.0071 nan 0.1000 0.0004
## 40 0.0018 nan 0.1000 -0.0000
## 60 0.0006 nan 0.1000 -0.0000
## 80 0.0003 nan 0.1000 -0.0000
## 100 0.0001 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold14: shrinkage=0.10, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold14: shrinkage=0.10, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0364 nan 0.1000 0.0044
## 2 0.0320 nan 0.1000 0.0046
## 3 0.0277 nan 0.1000 0.0025
## 4 0.0239 nan 0.1000 0.0024
## 5 0.0221 nan 0.1000 0.0014
## 6 0.0191 nan 0.1000 0.0011
## 7 0.0171 nan 0.1000 0.0003
## 8 0.0151 nan 0.1000 0.0017
## 9 0.0131 nan 0.1000 0.0014
## 10 0.0122 nan 0.1000 0.0006
## 20 0.0060 nan 0.1000 0.0003
## 40 0.0017 nan 0.1000 -0.0001
## 60 0.0006 nan 0.1000 0.0000
## 80 0.0003 nan 0.1000 0.0000
## 100 0.0001 nan 0.1000 -0.0000
## 120 0.0001 nan 0.1000 0.0000
## 140 0.0000 nan 0.1000 0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold14: shrinkage=0.10, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold14: shrinkage=0.10, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0393 nan 0.1000 0.0049
## 2 0.0332 nan 0.1000 0.0043
## 3 0.0287 nan 0.1000 0.0040
## 4 0.0260 nan 0.1000 0.0031
## 5 0.0230 nan 0.1000 0.0015
## 6 0.0209 nan 0.1000 0.0023
## 7 0.0188 nan 0.1000 0.0019
## 8 0.0172 nan 0.1000 -0.0006
## 9 0.0161 nan 0.1000 0.0002
## 10 0.0144 nan 0.1000 0.0017
## 20 0.0075 nan 0.1000 0.0006
## 40 0.0030 nan 0.1000 0.0000
## 60 0.0015 nan 0.1000 -0.0000
## 80 0.0010 nan 0.1000 -0.0000
## 100 0.0006 nan 0.1000 -0.0001
## 120 0.0003 nan 0.1000 -0.0000
## 140 0.0002 nan 0.1000 -0.0000
## 160 0.0002 nan 0.1000 0.0000
## 180 0.0001 nan 0.1000 0.0000
## 200 0.0001 nan 0.1000 0.0000
##
## - Fold14: shrinkage=0.10, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold14: shrinkage=0.10, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0402 nan 0.1000 0.0026
## 2 0.0352 nan 0.1000 0.0023
## 3 0.0308 nan 0.1000 0.0035
## 4 0.0268 nan 0.1000 0.0026
## 5 0.0227 nan 0.1000 0.0042
## 6 0.0207 nan 0.1000 -0.0014
## 7 0.0184 nan 0.1000 0.0013
## 8 0.0161 nan 0.1000 0.0010
## 9 0.0145 nan 0.1000 0.0014
## 10 0.0124 nan 0.1000 0.0014
## 20 0.0038 nan 0.1000 0.0005
## 40 0.0007 nan 0.1000 0.0001
## 60 0.0002 nan 0.1000 -0.0000
## 80 0.0000 nan 0.1000 0.0000
## 100 0.0000 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 0.0000
## 140 0.0000 nan 0.1000 0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold14: shrinkage=0.10, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold14: shrinkage=0.10, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0387 nan 0.1000 0.0032
## 2 0.0341 nan 0.1000 -0.0004
## 3 0.0300 nan 0.1000 0.0044
## 4 0.0260 nan 0.1000 0.0040
## 5 0.0230 nan 0.1000 0.0028
## 6 0.0206 nan 0.1000 0.0011
## 7 0.0184 nan 0.1000 0.0020
## 8 0.0154 nan 0.1000 0.0024
## 9 0.0137 nan 0.1000 0.0016
## 10 0.0121 nan 0.1000 0.0015
## 20 0.0054 nan 0.1000 -0.0004
## 40 0.0008 nan 0.1000 0.0001
## 60 0.0005 nan 0.1000 -0.0000
## 80 0.0002 nan 0.1000 0.0000
## 100 0.0001 nan 0.1000 -0.0000
## 120 0.0001 nan 0.1000 -0.0000
## 140 0.0001 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold14: shrinkage=0.10, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold14: shrinkage=0.10, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0396 nan 0.1000 0.0027
## 2 0.0338 nan 0.1000 0.0054
## 3 0.0307 nan 0.1000 0.0011
## 4 0.0271 nan 0.1000 0.0037
## 5 0.0238 nan 0.1000 0.0028
## 6 0.0214 nan 0.1000 0.0014
## 7 0.0199 nan 0.1000 0.0009
## 8 0.0193 nan 0.1000 -0.0019
## 9 0.0175 nan 0.1000 0.0018
## 10 0.0165 nan 0.1000 0.0007
## 20 0.0082 nan 0.1000 0.0003
## 40 0.0034 nan 0.1000 0.0000
## 60 0.0020 nan 0.1000 0.0000
## 80 0.0010 nan 0.1000 0.0000
## 100 0.0005 nan 0.1000 -0.0000
## 120 0.0004 nan 0.1000 -0.0000
## 140 0.0003 nan 0.1000 -0.0000
## 160 0.0002 nan 0.1000 0.0000
## 180 0.0001 nan 0.1000 0.0000
## 200 0.0001 nan 0.1000 -0.0000
##
## - Fold14: shrinkage=0.10, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold14: shrinkage=0.10, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0377 nan 0.1000 0.0042
## 2 0.0334 nan 0.1000 0.0054
## 3 0.0292 nan 0.1000 0.0018
## 4 0.0240 nan 0.1000 0.0041
## 5 0.0218 nan 0.1000 0.0016
## 6 0.0180 nan 0.1000 0.0031
## 7 0.0148 nan 0.1000 0.0026
## 8 0.0120 nan 0.1000 0.0028
## 9 0.0102 nan 0.1000 0.0006
## 10 0.0092 nan 0.1000 0.0001
## 20 0.0024 nan 0.1000 0.0002
## 40 0.0004 nan 0.1000 -0.0000
## 60 0.0001 nan 0.1000 -0.0000
## 80 0.0000 nan 0.1000 -0.0000
## 100 0.0000 nan 0.1000 0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 0.0000
##
## - Fold14: shrinkage=0.10, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold14: shrinkage=0.10, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0369 nan 0.1000 0.0045
## 2 0.0317 nan 0.1000 0.0049
## 3 0.0261 nan 0.1000 0.0027
## 4 0.0225 nan 0.1000 0.0041
## 5 0.0200 nan 0.1000 0.0005
## 6 0.0172 nan 0.1000 0.0011
## 7 0.0145 nan 0.1000 0.0017
## 8 0.0128 nan 0.1000 0.0007
## 9 0.0117 nan 0.1000 0.0004
## 10 0.0108 nan 0.1000 0.0007
## 20 0.0034 nan 0.1000 0.0004
## 40 0.0009 nan 0.1000 0.0000
## 60 0.0004 nan 0.1000 0.0000
## 80 0.0002 nan 0.1000 -0.0000
## 100 0.0001 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold14: shrinkage=0.10, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold14: shrinkage=0.10, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0380 nan 0.1000 0.0053
## 2 0.0347 nan 0.1000 0.0033
## 3 0.0312 nan 0.1000 0.0039
## 4 0.0281 nan 0.1000 0.0018
## 5 0.0258 nan 0.1000 0.0026
## 6 0.0228 nan 0.1000 0.0028
## 7 0.0213 nan 0.1000 0.0010
## 8 0.0182 nan 0.1000 0.0015
## 9 0.0158 nan 0.1000 0.0011
## 10 0.0141 nan 0.1000 0.0013
## 20 0.0081 nan 0.1000 0.0003
## 40 0.0036 nan 0.1000 -0.0001
## 60 0.0016 nan 0.1000 -0.0000
## 80 0.0009 nan 0.1000 -0.0000
## 100 0.0007 nan 0.1000 -0.0000
## 120 0.0004 nan 0.1000 0.0000
## 140 0.0002 nan 0.1000 -0.0000
## 160 0.0002 nan 0.1000 -0.0000
## 180 0.0001 nan 0.1000 -0.0000
## 200 0.0001 nan 0.1000 -0.0000
##
## - Fold14: shrinkage=0.10, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold15: shrinkage=0.01, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0367 nan 0.0100 0.0005
## 2 0.0363 nan 0.0100 0.0000
## 3 0.0359 nan 0.0100 0.0004
## 4 0.0354 nan 0.0100 0.0002
## 5 0.0350 nan 0.0100 0.0005
## 6 0.0344 nan 0.0100 0.0005
## 7 0.0340 nan 0.0100 0.0003
## 8 0.0334 nan 0.0100 0.0005
## 9 0.0331 nan 0.0100 0.0003
## 10 0.0328 nan 0.0100 0.0004
## 20 0.0293 nan 0.0100 0.0004
## 40 0.0234 nan 0.0100 0.0003
## 60 0.0189 nan 0.0100 0.0002
## 80 0.0159 nan 0.0100 0.0000
## 100 0.0134 nan 0.0100 -0.0000
## 120 0.0110 nan 0.0100 -0.0000
## 140 0.0092 nan 0.0100 0.0000
## 160 0.0079 nan 0.0100 0.0001
## 180 0.0067 nan 0.0100 0.0000
## 200 0.0058 nan 0.0100 0.0000
##
## - Fold15: shrinkage=0.01, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold15: shrinkage=0.01, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0366 nan 0.0100 0.0002
## 2 0.0362 nan 0.0100 0.0004
## 3 0.0357 nan 0.0100 0.0005
## 4 0.0355 nan 0.0100 0.0001
## 5 0.0351 nan 0.0100 0.0003
## 6 0.0346 nan 0.0100 0.0003
## 7 0.0342 nan 0.0100 0.0004
## 8 0.0337 nan 0.0100 0.0004
## 9 0.0332 nan 0.0100 0.0004
## 10 0.0328 nan 0.0100 0.0004
## 20 0.0291 nan 0.0100 0.0002
## 40 0.0232 nan 0.0100 0.0003
## 60 0.0192 nan 0.0100 0.0002
## 80 0.0158 nan 0.0100 0.0002
## 100 0.0131 nan 0.0100 0.0001
## 120 0.0113 nan 0.0100 0.0001
## 140 0.0097 nan 0.0100 0.0000
## 160 0.0084 nan 0.0100 0.0000
## 180 0.0071 nan 0.0100 0.0000
## 200 0.0062 nan 0.0100 -0.0000
##
## - Fold15: shrinkage=0.01, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold15: shrinkage=0.01, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0366 nan 0.0100 0.0005
## 2 0.0362 nan 0.0100 0.0002
## 3 0.0358 nan 0.0100 0.0003
## 4 0.0353 nan 0.0100 0.0005
## 5 0.0350 nan 0.0100 0.0002
## 6 0.0346 nan 0.0100 0.0003
## 7 0.0341 nan 0.0100 0.0005
## 8 0.0336 nan 0.0100 0.0003
## 9 0.0333 nan 0.0100 0.0000
## 10 0.0329 nan 0.0100 0.0005
## 20 0.0295 nan 0.0100 0.0003
## 40 0.0237 nan 0.0100 0.0001
## 60 0.0193 nan 0.0100 0.0000
## 80 0.0158 nan 0.0100 0.0001
## 100 0.0134 nan 0.0100 0.0001
## 120 0.0115 nan 0.0100 0.0001
## 140 0.0101 nan 0.0100 0.0000
## 160 0.0086 nan 0.0100 -0.0000
## 180 0.0076 nan 0.0100 -0.0000
## 200 0.0068 nan 0.0100 -0.0000
##
## - Fold15: shrinkage=0.01, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold15: shrinkage=0.01, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0366 nan 0.0100 0.0005
## 2 0.0361 nan 0.0100 0.0006
## 3 0.0358 nan 0.0100 0.0001
## 4 0.0352 nan 0.0100 0.0006
## 5 0.0346 nan 0.0100 0.0004
## 6 0.0342 nan 0.0100 0.0003
## 7 0.0339 nan 0.0100 0.0002
## 8 0.0334 nan 0.0100 0.0003
## 9 0.0329 nan 0.0100 0.0005
## 10 0.0323 nan 0.0100 0.0004
## 20 0.0277 nan 0.0100 0.0003
## 40 0.0209 nan 0.0100 0.0003
## 60 0.0168 nan 0.0100 -0.0000
## 80 0.0129 nan 0.0100 0.0001
## 100 0.0102 nan 0.0100 0.0001
## 120 0.0081 nan 0.0100 0.0001
## 140 0.0065 nan 0.0100 0.0001
## 160 0.0054 nan 0.0100 -0.0000
## 180 0.0044 nan 0.0100 0.0000
## 200 0.0035 nan 0.0100 0.0000
##
## - Fold15: shrinkage=0.01, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold15: shrinkage=0.01, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0367 nan 0.0100 0.0003
## 2 0.0363 nan 0.0100 0.0004
## 3 0.0357 nan 0.0100 0.0004
## 4 0.0354 nan 0.0100 0.0002
## 5 0.0348 nan 0.0100 0.0006
## 6 0.0344 nan 0.0100 0.0004
## 7 0.0342 nan 0.0100 0.0000
## 8 0.0337 nan 0.0100 0.0005
## 9 0.0334 nan 0.0100 0.0002
## 10 0.0329 nan 0.0100 0.0003
## 20 0.0286 nan 0.0100 0.0004
## 40 0.0226 nan 0.0100 0.0004
## 60 0.0179 nan 0.0100 0.0000
## 80 0.0141 nan 0.0100 0.0001
## 100 0.0113 nan 0.0100 0.0000
## 120 0.0091 nan 0.0100 0.0001
## 140 0.0074 nan 0.0100 0.0000
## 160 0.0061 nan 0.0100 0.0000
## 180 0.0051 nan 0.0100 0.0000
## 200 0.0042 nan 0.0100 0.0000
##
## - Fold15: shrinkage=0.01, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold15: shrinkage=0.01, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0367 nan 0.0100 0.0003
## 2 0.0362 nan 0.0100 0.0005
## 3 0.0356 nan 0.0100 0.0005
## 4 0.0352 nan 0.0100 0.0002
## 5 0.0348 nan 0.0100 0.0003
## 6 0.0343 nan 0.0100 0.0004
## 7 0.0338 nan 0.0100 0.0004
## 8 0.0333 nan 0.0100 0.0003
## 9 0.0329 nan 0.0100 0.0004
## 10 0.0325 nan 0.0100 0.0003
## 20 0.0286 nan 0.0100 0.0002
## 40 0.0230 nan 0.0100 -0.0001
## 60 0.0187 nan 0.0100 0.0001
## 80 0.0156 nan 0.0100 0.0001
## 100 0.0131 nan 0.0100 0.0001
## 120 0.0114 nan 0.0100 0.0001
## 140 0.0100 nan 0.0100 0.0001
## 160 0.0090 nan 0.0100 0.0000
## 180 0.0080 nan 0.0100 0.0000
## 200 0.0072 nan 0.0100 0.0000
##
## - Fold15: shrinkage=0.01, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold15: shrinkage=0.01, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0366 nan 0.0100 0.0003
## 2 0.0360 nan 0.0100 0.0003
## 3 0.0353 nan 0.0100 0.0005
## 4 0.0348 nan 0.0100 0.0005
## 5 0.0342 nan 0.0100 0.0006
## 6 0.0337 nan 0.0100 0.0005
## 7 0.0331 nan 0.0100 0.0003
## 8 0.0325 nan 0.0100 0.0004
## 9 0.0321 nan 0.0100 0.0001
## 10 0.0316 nan 0.0100 0.0004
## 20 0.0273 nan 0.0100 0.0001
## 40 0.0205 nan 0.0100 0.0002
## 60 0.0157 nan 0.0100 0.0002
## 80 0.0120 nan 0.0100 0.0000
## 100 0.0093 nan 0.0100 0.0001
## 120 0.0072 nan 0.0100 0.0001
## 140 0.0054 nan 0.0100 0.0001
## 160 0.0043 nan 0.0100 0.0000
## 180 0.0033 nan 0.0100 0.0000
## 200 0.0027 nan 0.0100 0.0000
##
## - Fold15: shrinkage=0.01, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold15: shrinkage=0.01, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0365 nan 0.0100 0.0004
## 2 0.0358 nan 0.0100 0.0005
## 3 0.0352 nan 0.0100 0.0003
## 4 0.0348 nan 0.0100 0.0002
## 5 0.0343 nan 0.0100 0.0003
## 6 0.0338 nan 0.0100 0.0005
## 7 0.0334 nan 0.0100 0.0003
## 8 0.0328 nan 0.0100 0.0005
## 9 0.0324 nan 0.0100 0.0005
## 10 0.0318 nan 0.0100 0.0004
## 20 0.0278 nan 0.0100 0.0003
## 40 0.0213 nan 0.0100 0.0003
## 60 0.0169 nan 0.0100 0.0002
## 80 0.0132 nan 0.0100 0.0001
## 100 0.0105 nan 0.0100 0.0001
## 120 0.0085 nan 0.0100 0.0001
## 140 0.0071 nan 0.0100 -0.0000
## 160 0.0057 nan 0.0100 -0.0000
## 180 0.0047 nan 0.0100 0.0001
## 200 0.0039 nan 0.0100 -0.0000
##
## - Fold15: shrinkage=0.01, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold15: shrinkage=0.01, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0366 nan 0.0100 0.0006
## 2 0.0361 nan 0.0100 0.0005
## 3 0.0355 nan 0.0100 0.0005
## 4 0.0350 nan 0.0100 0.0004
## 5 0.0346 nan 0.0100 0.0004
## 6 0.0342 nan 0.0100 0.0003
## 7 0.0337 nan 0.0100 0.0005
## 8 0.0335 nan 0.0100 0.0000
## 9 0.0332 nan 0.0100 0.0003
## 10 0.0328 nan 0.0100 0.0000
## 20 0.0290 nan 0.0100 0.0003
## 40 0.0234 nan 0.0100 0.0003
## 60 0.0187 nan 0.0100 0.0002
## 80 0.0156 nan 0.0100 0.0001
## 100 0.0132 nan 0.0100 0.0000
## 120 0.0113 nan 0.0100 0.0001
## 140 0.0099 nan 0.0100 0.0000
## 160 0.0087 nan 0.0100 0.0000
## 180 0.0078 nan 0.0100 0.0000
## 200 0.0070 nan 0.0100 0.0000
##
## - Fold15: shrinkage=0.01, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold15: shrinkage=0.05, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0348 nan 0.0500 0.0023
## 2 0.0324 nan 0.0500 0.0023
## 3 0.0306 nan 0.0500 0.0016
## 4 0.0291 nan 0.0500 0.0015
## 5 0.0273 nan 0.0500 0.0007
## 6 0.0261 nan 0.0500 0.0009
## 7 0.0247 nan 0.0500 0.0004
## 8 0.0234 nan 0.0500 0.0014
## 9 0.0229 nan 0.0500 -0.0003
## 10 0.0220 nan 0.0500 0.0006
## 20 0.0137 nan 0.0500 0.0007
## 40 0.0066 nan 0.0500 0.0000
## 60 0.0034 nan 0.0500 0.0001
## 80 0.0017 nan 0.0500 -0.0000
## 100 0.0011 nan 0.0500 -0.0000
## 120 0.0007 nan 0.0500 -0.0000
## 140 0.0004 nan 0.0500 0.0000
## 160 0.0002 nan 0.0500 0.0000
## 180 0.0002 nan 0.0500 -0.0000
## 200 0.0001 nan 0.0500 -0.0000
##
## - Fold15: shrinkage=0.05, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold15: shrinkage=0.05, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0350 nan 0.0500 0.0024
## 2 0.0333 nan 0.0500 0.0018
## 3 0.0310 nan 0.0500 0.0023
## 4 0.0306 nan 0.0500 -0.0005
## 5 0.0287 nan 0.0500 0.0018
## 6 0.0268 nan 0.0500 0.0015
## 7 0.0253 nan 0.0500 0.0015
## 8 0.0238 nan 0.0500 0.0008
## 9 0.0226 nan 0.0500 0.0011
## 10 0.0219 nan 0.0500 0.0001
## 20 0.0138 nan 0.0500 0.0006
## 40 0.0060 nan 0.0500 0.0000
## 60 0.0037 nan 0.0500 0.0001
## 80 0.0021 nan 0.0500 0.0000
## 100 0.0012 nan 0.0500 -0.0000
## 120 0.0008 nan 0.0500 -0.0000
## 140 0.0005 nan 0.0500 -0.0000
## 160 0.0003 nan 0.0500 0.0000
## 180 0.0002 nan 0.0500 -0.0000
## 200 0.0001 nan 0.0500 0.0000
##
## - Fold15: shrinkage=0.05, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold15: shrinkage=0.05, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0353 nan 0.0500 0.0012
## 2 0.0329 nan 0.0500 0.0020
## 3 0.0306 nan 0.0500 0.0020
## 4 0.0285 nan 0.0500 0.0018
## 5 0.0266 nan 0.0500 0.0019
## 6 0.0259 nan 0.0500 0.0006
## 7 0.0245 nan 0.0500 0.0013
## 8 0.0239 nan 0.0500 0.0000
## 9 0.0224 nan 0.0500 0.0011
## 10 0.0212 nan 0.0500 0.0010
## 20 0.0138 nan 0.0500 0.0001
## 40 0.0072 nan 0.0500 0.0002
## 60 0.0043 nan 0.0500 -0.0000
## 80 0.0029 nan 0.0500 0.0000
## 100 0.0021 nan 0.0500 0.0000
## 120 0.0015 nan 0.0500 -0.0000
## 140 0.0011 nan 0.0500 -0.0000
## 160 0.0009 nan 0.0500 -0.0000
## 180 0.0007 nan 0.0500 -0.0000
## 200 0.0006 nan 0.0500 -0.0000
##
## - Fold15: shrinkage=0.05, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold15: shrinkage=0.05, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0361 nan 0.0500 0.0002
## 2 0.0335 nan 0.0500 0.0022
## 3 0.0309 nan 0.0500 0.0014
## 4 0.0285 nan 0.0500 0.0019
## 5 0.0270 nan 0.0500 -0.0004
## 6 0.0250 nan 0.0500 0.0015
## 7 0.0239 nan 0.0500 0.0010
## 8 0.0222 nan 0.0500 0.0007
## 9 0.0215 nan 0.0500 -0.0006
## 10 0.0198 nan 0.0500 0.0013
## 20 0.0101 nan 0.0500 0.0006
## 40 0.0038 nan 0.0500 0.0001
## 60 0.0017 nan 0.0500 0.0000
## 80 0.0008 nan 0.0500 -0.0000
## 100 0.0004 nan 0.0500 -0.0000
## 120 0.0002 nan 0.0500 -0.0000
## 140 0.0001 nan 0.0500 -0.0000
## 160 0.0001 nan 0.0500 -0.0000
## 180 0.0000 nan 0.0500 -0.0000
## 200 0.0000 nan 0.0500 0.0000
##
## - Fold15: shrinkage=0.05, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold15: shrinkage=0.05, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0346 nan 0.0500 0.0017
## 2 0.0322 nan 0.0500 0.0018
## 3 0.0301 nan 0.0500 0.0010
## 4 0.0280 nan 0.0500 0.0019
## 5 0.0263 nan 0.0500 0.0014
## 6 0.0248 nan 0.0500 0.0008
## 7 0.0228 nan 0.0500 0.0017
## 8 0.0211 nan 0.0500 0.0008
## 9 0.0196 nan 0.0500 0.0006
## 10 0.0183 nan 0.0500 0.0013
## 20 0.0102 nan 0.0500 0.0005
## 40 0.0040 nan 0.0500 0.0000
## 60 0.0017 nan 0.0500 -0.0000
## 80 0.0009 nan 0.0500 -0.0000
## 100 0.0006 nan 0.0500 -0.0000
## 120 0.0004 nan 0.0500 -0.0000
## 140 0.0002 nan 0.0500 -0.0000
## 160 0.0001 nan 0.0500 -0.0000
## 180 0.0001 nan 0.0500 0.0000
## 200 0.0001 nan 0.0500 -0.0000
##
## - Fold15: shrinkage=0.05, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold15: shrinkage=0.05, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0346 nan 0.0500 0.0012
## 2 0.0325 nan 0.0500 0.0021
## 3 0.0312 nan 0.0500 -0.0001
## 4 0.0296 nan 0.0500 0.0018
## 5 0.0279 nan 0.0500 0.0019
## 6 0.0263 nan 0.0500 0.0002
## 7 0.0252 nan 0.0500 0.0003
## 8 0.0241 nan 0.0500 0.0012
## 9 0.0225 nan 0.0500 0.0010
## 10 0.0214 nan 0.0500 0.0006
## 20 0.0135 nan 0.0500 0.0001
## 40 0.0068 nan 0.0500 0.0000
## 60 0.0044 nan 0.0500 -0.0001
## 80 0.0027 nan 0.0500 0.0000
## 100 0.0019 nan 0.0500 0.0000
## 120 0.0014 nan 0.0500 -0.0000
## 140 0.0012 nan 0.0500 -0.0000
## 160 0.0010 nan 0.0500 -0.0000
## 180 0.0007 nan 0.0500 -0.0000
## 200 0.0006 nan 0.0500 -0.0000
##
## - Fold15: shrinkage=0.05, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold15: shrinkage=0.05, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0341 nan 0.0500 0.0035
## 2 0.0314 nan 0.0500 0.0012
## 3 0.0299 nan 0.0500 0.0004
## 4 0.0281 nan 0.0500 0.0012
## 5 0.0260 nan 0.0500 0.0017
## 6 0.0248 nan 0.0500 0.0010
## 7 0.0231 nan 0.0500 0.0014
## 8 0.0222 nan 0.0500 0.0005
## 9 0.0210 nan 0.0500 0.0005
## 10 0.0200 nan 0.0500 0.0002
## 20 0.0102 nan 0.0500 0.0004
## 40 0.0041 nan 0.0500 0.0000
## 60 0.0013 nan 0.0500 -0.0000
## 80 0.0006 nan 0.0500 -0.0000
## 100 0.0002 nan 0.0500 -0.0000
## 120 0.0001 nan 0.0500 -0.0000
## 140 0.0001 nan 0.0500 -0.0000
## 160 0.0000 nan 0.0500 -0.0000
## 180 0.0000 nan 0.0500 -0.0000
## 200 0.0000 nan 0.0500 -0.0000
##
## - Fold15: shrinkage=0.05, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold15: shrinkage=0.05, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0360 nan 0.0500 0.0001
## 2 0.0334 nan 0.0500 0.0022
## 3 0.0312 nan 0.0500 0.0014
## 4 0.0294 nan 0.0500 0.0012
## 5 0.0278 nan 0.0500 0.0015
## 6 0.0262 nan 0.0500 0.0013
## 7 0.0248 nan 0.0500 0.0006
## 8 0.0230 nan 0.0500 0.0022
## 9 0.0216 nan 0.0500 0.0014
## 10 0.0199 nan 0.0500 0.0008
## 20 0.0117 nan 0.0500 0.0006
## 40 0.0044 nan 0.0500 0.0002
## 60 0.0022 nan 0.0500 -0.0000
## 80 0.0011 nan 0.0500 -0.0000
## 100 0.0007 nan 0.0500 -0.0000
## 120 0.0004 nan 0.0500 -0.0000
## 140 0.0002 nan 0.0500 -0.0000
## 160 0.0002 nan 0.0500 -0.0000
## 180 0.0001 nan 0.0500 -0.0000
## 200 0.0001 nan 0.0500 -0.0000
##
## - Fold15: shrinkage=0.05, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold15: shrinkage=0.05, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0352 nan 0.0500 0.0018
## 2 0.0338 nan 0.0500 -0.0005
## 3 0.0317 nan 0.0500 0.0020
## 4 0.0297 nan 0.0500 0.0021
## 5 0.0279 nan 0.0500 0.0010
## 6 0.0264 nan 0.0500 0.0017
## 7 0.0251 nan 0.0500 0.0006
## 8 0.0242 nan 0.0500 0.0003
## 9 0.0229 nan 0.0500 0.0012
## 10 0.0221 nan 0.0500 0.0008
## 20 0.0150 nan 0.0500 0.0003
## 40 0.0078 nan 0.0500 0.0001
## 60 0.0046 nan 0.0500 -0.0000
## 80 0.0032 nan 0.0500 0.0000
## 100 0.0021 nan 0.0500 -0.0000
## 120 0.0015 nan 0.0500 -0.0000
## 140 0.0011 nan 0.0500 0.0000
## 160 0.0008 nan 0.0500 0.0000
## 180 0.0007 nan 0.0500 -0.0000
## 200 0.0005 nan 0.0500 -0.0000
##
## - Fold15: shrinkage=0.05, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold15: shrinkage=0.10, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0317 nan 0.1000 0.0052
## 2 0.0290 nan 0.1000 -0.0002
## 3 0.0259 nan 0.1000 0.0022
## 4 0.0234 nan 0.1000 0.0024
## 5 0.0225 nan 0.1000 -0.0007
## 6 0.0204 nan 0.1000 0.0021
## 7 0.0187 nan 0.1000 0.0020
## 8 0.0176 nan 0.1000 0.0000
## 9 0.0166 nan 0.1000 -0.0003
## 10 0.0147 nan 0.1000 0.0019
## 20 0.0066 nan 0.1000 -0.0000
## 40 0.0014 nan 0.1000 0.0000
## 60 0.0005 nan 0.1000 -0.0000
## 80 0.0002 nan 0.1000 -0.0000
## 100 0.0001 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 0.0000
##
## - Fold15: shrinkage=0.10, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold15: shrinkage=0.10, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0320 nan 0.1000 0.0043
## 2 0.0281 nan 0.1000 0.0041
## 3 0.0239 nan 0.1000 0.0021
## 4 0.0221 nan 0.1000 0.0023
## 5 0.0205 nan 0.1000 0.0014
## 6 0.0188 nan 0.1000 0.0012
## 7 0.0160 nan 0.1000 0.0017
## 8 0.0148 nan 0.1000 0.0007
## 9 0.0139 nan 0.1000 -0.0002
## 10 0.0132 nan 0.1000 0.0000
## 20 0.0074 nan 0.1000 0.0005
## 40 0.0022 nan 0.1000 -0.0000
## 60 0.0008 nan 0.1000 0.0000
## 80 0.0003 nan 0.1000 0.0000
## 100 0.0001 nan 0.1000 -0.0000
## 120 0.0001 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 0.0000
##
## - Fold15: shrinkage=0.10, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold15: shrinkage=0.10, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0325 nan 0.1000 0.0047
## 2 0.0291 nan 0.1000 0.0030
## 3 0.0249 nan 0.1000 0.0033
## 4 0.0218 nan 0.1000 0.0017
## 5 0.0198 nan 0.1000 0.0024
## 6 0.0184 nan 0.1000 -0.0013
## 7 0.0172 nan 0.1000 0.0008
## 8 0.0146 nan 0.1000 0.0015
## 9 0.0139 nan 0.1000 0.0005
## 10 0.0132 nan 0.1000 0.0003
## 20 0.0073 nan 0.1000 0.0005
## 40 0.0032 nan 0.1000 -0.0000
## 60 0.0016 nan 0.1000 0.0000
## 80 0.0008 nan 0.1000 -0.0001
## 100 0.0005 nan 0.1000 -0.0000
## 120 0.0003 nan 0.1000 -0.0000
## 140 0.0002 nan 0.1000 -0.0000
## 160 0.0001 nan 0.1000 -0.0000
## 180 0.0001 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 0.0000
##
## - Fold15: shrinkage=0.10, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold15: shrinkage=0.10, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0327 nan 0.1000 0.0041
## 2 0.0274 nan 0.1000 0.0059
## 3 0.0236 nan 0.1000 0.0030
## 4 0.0196 nan 0.1000 0.0032
## 5 0.0168 nan 0.1000 0.0013
## 6 0.0152 nan 0.1000 0.0009
## 7 0.0132 nan 0.1000 0.0015
## 8 0.0114 nan 0.1000 0.0013
## 9 0.0099 nan 0.1000 0.0009
## 10 0.0089 nan 0.1000 0.0004
## 20 0.0034 nan 0.1000 0.0007
## 40 0.0006 nan 0.1000 -0.0000
## 60 0.0002 nan 0.1000 -0.0000
## 80 0.0001 nan 0.1000 -0.0000
## 100 0.0000 nan 0.1000 0.0000
## 120 0.0000 nan 0.1000 0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold15: shrinkage=0.10, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold15: shrinkage=0.10, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0332 nan 0.1000 0.0024
## 2 0.0286 nan 0.1000 0.0024
## 3 0.0254 nan 0.1000 0.0028
## 4 0.0234 nan 0.1000 0.0012
## 5 0.0217 nan 0.1000 0.0016
## 6 0.0196 nan 0.1000 -0.0006
## 7 0.0175 nan 0.1000 -0.0000
## 8 0.0154 nan 0.1000 0.0015
## 9 0.0139 nan 0.1000 0.0010
## 10 0.0127 nan 0.1000 0.0008
## 20 0.0049 nan 0.1000 0.0001
## 40 0.0011 nan 0.1000 -0.0001
## 60 0.0003 nan 0.1000 -0.0000
## 80 0.0001 nan 0.1000 -0.0000
## 100 0.0000 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold15: shrinkage=0.10, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold15: shrinkage=0.10, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0336 nan 0.1000 0.0027
## 2 0.0313 nan 0.1000 0.0001
## 3 0.0272 nan 0.1000 0.0025
## 4 0.0249 nan 0.1000 0.0022
## 5 0.0228 nan 0.1000 0.0014
## 6 0.0203 nan 0.1000 0.0023
## 7 0.0189 nan 0.1000 0.0012
## 8 0.0170 nan 0.1000 0.0014
## 9 0.0156 nan 0.1000 0.0008
## 10 0.0147 nan 0.1000 0.0000
## 20 0.0079 nan 0.1000 -0.0001
## 40 0.0029 nan 0.1000 -0.0003
## 60 0.0014 nan 0.1000 -0.0001
## 80 0.0007 nan 0.1000 -0.0000
## 100 0.0004 nan 0.1000 -0.0000
## 120 0.0002 nan 0.1000 -0.0000
## 140 0.0001 nan 0.1000 -0.0000
## 160 0.0001 nan 0.1000 0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold15: shrinkage=0.10, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold15: shrinkage=0.10, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0329 nan 0.1000 0.0001
## 2 0.0287 nan 0.1000 0.0011
## 3 0.0260 nan 0.1000 0.0024
## 4 0.0226 nan 0.1000 0.0038
## 5 0.0194 nan 0.1000 0.0022
## 6 0.0170 nan 0.1000 0.0023
## 7 0.0138 nan 0.1000 0.0020
## 8 0.0124 nan 0.1000 0.0010
## 9 0.0121 nan 0.1000 -0.0003
## 10 0.0106 nan 0.1000 0.0012
## 20 0.0031 nan 0.1000 0.0003
## 40 0.0004 nan 0.1000 -0.0000
## 60 0.0001 nan 0.1000 -0.0000
## 80 0.0000 nan 0.1000 0.0000
## 100 0.0000 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold15: shrinkage=0.10, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold15: shrinkage=0.10, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0317 nan 0.1000 0.0048
## 2 0.0276 nan 0.1000 0.0035
## 3 0.0237 nan 0.1000 0.0040
## 4 0.0190 nan 0.1000 0.0021
## 5 0.0167 nan 0.1000 0.0024
## 6 0.0140 nan 0.1000 0.0009
## 7 0.0121 nan 0.1000 0.0015
## 8 0.0107 nan 0.1000 0.0010
## 9 0.0092 nan 0.1000 -0.0001
## 10 0.0079 nan 0.1000 0.0007
## 20 0.0033 nan 0.1000 -0.0001
## 40 0.0010 nan 0.1000 -0.0000
## 60 0.0004 nan 0.1000 -0.0000
## 80 0.0002 nan 0.1000 -0.0000
## 100 0.0001 nan 0.1000 -0.0000
## 120 0.0001 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold15: shrinkage=0.10, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold15: shrinkage=0.10, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0318 nan 0.1000 0.0049
## 2 0.0279 nan 0.1000 0.0015
## 3 0.0247 nan 0.1000 0.0036
## 4 0.0224 nan 0.1000 0.0024
## 5 0.0200 nan 0.1000 0.0018
## 6 0.0186 nan 0.1000 0.0002
## 7 0.0176 nan 0.1000 0.0008
## 8 0.0160 nan 0.1000 0.0008
## 9 0.0146 nan 0.1000 0.0007
## 10 0.0134 nan 0.1000 0.0010
## 20 0.0068 nan 0.1000 0.0000
## 40 0.0029 nan 0.1000 0.0000
## 60 0.0013 nan 0.1000 -0.0000
## 80 0.0008 nan 0.1000 0.0000
## 100 0.0005 nan 0.1000 -0.0000
## 120 0.0003 nan 0.1000 0.0000
## 140 0.0002 nan 0.1000 0.0000
## 160 0.0001 nan 0.1000 -0.0000
## 180 0.0001 nan 0.1000 -0.0000
## 200 0.0001 nan 0.1000 -0.0000
##
## - Fold15: shrinkage=0.10, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold16: shrinkage=0.01, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0434 nan 0.0100 0.0002
## 2 0.0427 nan 0.0100 0.0006
## 3 0.0423 nan 0.0100 0.0004
## 4 0.0418 nan 0.0100 0.0005
## 5 0.0414 nan 0.0100 0.0002
## 6 0.0408 nan 0.0100 0.0005
## 7 0.0404 nan 0.0100 0.0003
## 8 0.0399 nan 0.0100 0.0004
## 9 0.0394 nan 0.0100 0.0004
## 10 0.0390 nan 0.0100 0.0000
## 20 0.0347 nan 0.0100 0.0003
## 40 0.0272 nan 0.0100 0.0002
## 60 0.0218 nan 0.0100 0.0001
## 80 0.0173 nan 0.0100 0.0002
## 100 0.0143 nan 0.0100 0.0001
## 120 0.0120 nan 0.0100 0.0000
## 140 0.0102 nan 0.0100 0.0000
## 160 0.0086 nan 0.0100 0.0001
## 180 0.0073 nan 0.0100 0.0000
## 200 0.0061 nan 0.0100 0.0001
##
## - Fold16: shrinkage=0.01, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold16: shrinkage=0.01, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0433 nan 0.0100 0.0000
## 2 0.0428 nan 0.0100 0.0005
## 3 0.0422 nan 0.0100 0.0006
## 4 0.0416 nan 0.0100 0.0005
## 5 0.0411 nan 0.0100 0.0005
## 6 0.0405 nan 0.0100 0.0005
## 7 0.0401 nan 0.0100 0.0003
## 8 0.0395 nan 0.0100 0.0006
## 9 0.0389 nan 0.0100 0.0005
## 10 0.0386 nan 0.0100 0.0000
## 20 0.0347 nan 0.0100 0.0001
## 40 0.0284 nan 0.0100 0.0003
## 60 0.0226 nan 0.0100 0.0003
## 80 0.0187 nan 0.0100 0.0002
## 100 0.0154 nan 0.0100 0.0001
## 120 0.0129 nan 0.0100 -0.0000
## 140 0.0109 nan 0.0100 0.0000
## 160 0.0092 nan 0.0100 0.0000
## 180 0.0079 nan 0.0100 0.0000
## 200 0.0067 nan 0.0100 0.0000
##
## - Fold16: shrinkage=0.01, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold16: shrinkage=0.01, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0433 nan 0.0100 0.0005
## 2 0.0426 nan 0.0100 0.0005
## 3 0.0421 nan 0.0100 0.0006
## 4 0.0416 nan 0.0100 0.0003
## 5 0.0412 nan 0.0100 0.0004
## 6 0.0407 nan 0.0100 0.0001
## 7 0.0401 nan 0.0100 0.0005
## 8 0.0396 nan 0.0100 0.0004
## 9 0.0390 nan 0.0100 0.0005
## 10 0.0386 nan 0.0100 0.0002
## 20 0.0347 nan 0.0100 0.0005
## 40 0.0278 nan 0.0100 0.0003
## 60 0.0226 nan 0.0100 0.0003
## 80 0.0189 nan 0.0100 0.0001
## 100 0.0160 nan 0.0100 0.0002
## 120 0.0137 nan 0.0100 0.0000
## 140 0.0114 nan 0.0100 -0.0000
## 160 0.0101 nan 0.0100 0.0001
## 180 0.0088 nan 0.0100 -0.0000
## 200 0.0079 nan 0.0100 0.0000
##
## - Fold16: shrinkage=0.01, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold16: shrinkage=0.01, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0436 nan 0.0100 -0.0003
## 2 0.0432 nan 0.0100 0.0005
## 3 0.0426 nan 0.0100 0.0004
## 4 0.0419 nan 0.0100 0.0004
## 5 0.0411 nan 0.0100 0.0007
## 6 0.0406 nan 0.0100 0.0005
## 7 0.0401 nan 0.0100 0.0006
## 8 0.0396 nan 0.0100 0.0003
## 9 0.0390 nan 0.0100 0.0006
## 10 0.0384 nan 0.0100 0.0005
## 20 0.0331 nan 0.0100 0.0005
## 40 0.0256 nan 0.0100 0.0003
## 60 0.0195 nan 0.0100 0.0001
## 80 0.0150 nan 0.0100 0.0002
## 100 0.0119 nan 0.0100 0.0001
## 120 0.0091 nan 0.0100 0.0001
## 140 0.0072 nan 0.0100 -0.0000
## 160 0.0058 nan 0.0100 0.0000
## 180 0.0046 nan 0.0100 0.0000
## 200 0.0037 nan 0.0100 0.0000
##
## - Fold16: shrinkage=0.01, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold16: shrinkage=0.01, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0430 nan 0.0100 0.0006
## 2 0.0423 nan 0.0100 0.0005
## 3 0.0417 nan 0.0100 0.0002
## 4 0.0412 nan 0.0100 0.0003
## 5 0.0407 nan 0.0100 0.0004
## 6 0.0401 nan 0.0100 0.0004
## 7 0.0393 nan 0.0100 0.0006
## 8 0.0390 nan 0.0100 -0.0000
## 9 0.0383 nan 0.0100 0.0005
## 10 0.0376 nan 0.0100 0.0005
## 20 0.0325 nan 0.0100 0.0002
## 40 0.0251 nan 0.0100 0.0003
## 60 0.0195 nan 0.0100 0.0002
## 80 0.0154 nan 0.0100 0.0001
## 100 0.0128 nan 0.0100 0.0000
## 120 0.0104 nan 0.0100 0.0000
## 140 0.0084 nan 0.0100 0.0001
## 160 0.0066 nan 0.0100 0.0001
## 180 0.0056 nan 0.0100 0.0000
## 200 0.0047 nan 0.0100 0.0000
##
## - Fold16: shrinkage=0.01, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold16: shrinkage=0.01, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0432 nan 0.0100 0.0005
## 2 0.0427 nan 0.0100 0.0004
## 3 0.0420 nan 0.0100 0.0006
## 4 0.0414 nan 0.0100 0.0006
## 5 0.0408 nan 0.0100 0.0005
## 6 0.0402 nan 0.0100 0.0006
## 7 0.0399 nan 0.0100 0.0001
## 8 0.0397 nan 0.0100 0.0000
## 9 0.0393 nan 0.0100 0.0003
## 10 0.0388 nan 0.0100 0.0005
## 20 0.0352 nan 0.0100 0.0001
## 40 0.0283 nan 0.0100 0.0002
## 60 0.0231 nan 0.0100 0.0001
## 80 0.0195 nan 0.0100 0.0001
## 100 0.0161 nan 0.0100 0.0001
## 120 0.0138 nan 0.0100 0.0001
## 140 0.0119 nan 0.0100 0.0001
## 160 0.0103 nan 0.0100 0.0000
## 180 0.0090 nan 0.0100 -0.0000
## 200 0.0082 nan 0.0100 -0.0000
##
## - Fold16: shrinkage=0.01, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold16: shrinkage=0.01, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0434 nan 0.0100 0.0001
## 2 0.0425 nan 0.0100 0.0008
## 3 0.0420 nan 0.0100 0.0003
## 4 0.0414 nan 0.0100 0.0003
## 5 0.0407 nan 0.0100 0.0007
## 6 0.0400 nan 0.0100 0.0008
## 7 0.0394 nan 0.0100 0.0003
## 8 0.0385 nan 0.0100 0.0007
## 9 0.0379 nan 0.0100 0.0005
## 10 0.0373 nan 0.0100 0.0003
## 20 0.0320 nan 0.0100 0.0004
## 40 0.0243 nan 0.0100 0.0003
## 60 0.0188 nan 0.0100 0.0003
## 80 0.0144 nan 0.0100 -0.0000
## 100 0.0109 nan 0.0100 0.0000
## 120 0.0083 nan 0.0100 -0.0000
## 140 0.0066 nan 0.0100 0.0000
## 160 0.0053 nan 0.0100 0.0000
## 180 0.0042 nan 0.0100 0.0000
## 200 0.0033 nan 0.0100 0.0000
##
## - Fold16: shrinkage=0.01, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold16: shrinkage=0.01, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0433 nan 0.0100 0.0004
## 2 0.0428 nan 0.0100 0.0004
## 3 0.0421 nan 0.0100 0.0007
## 4 0.0417 nan 0.0100 0.0003
## 5 0.0409 nan 0.0100 0.0004
## 6 0.0401 nan 0.0100 0.0003
## 7 0.0394 nan 0.0100 0.0006
## 8 0.0388 nan 0.0100 0.0004
## 9 0.0384 nan 0.0100 0.0004
## 10 0.0379 nan 0.0100 0.0004
## 20 0.0328 nan 0.0100 0.0003
## 40 0.0245 nan 0.0100 0.0002
## 60 0.0186 nan 0.0100 0.0002
## 80 0.0145 nan 0.0100 0.0002
## 100 0.0115 nan 0.0100 0.0001
## 120 0.0090 nan 0.0100 0.0000
## 140 0.0072 nan 0.0100 0.0000
## 160 0.0058 nan 0.0100 0.0000
## 180 0.0048 nan 0.0100 0.0000
## 200 0.0039 nan 0.0100 0.0000
##
## - Fold16: shrinkage=0.01, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold16: shrinkage=0.01, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0432 nan 0.0100 0.0004
## 2 0.0425 nan 0.0100 0.0005
## 3 0.0422 nan 0.0100 0.0003
## 4 0.0418 nan 0.0100 0.0003
## 5 0.0413 nan 0.0100 0.0004
## 6 0.0409 nan 0.0100 0.0003
## 7 0.0402 nan 0.0100 0.0005
## 8 0.0400 nan 0.0100 -0.0002
## 9 0.0394 nan 0.0100 0.0005
## 10 0.0388 nan 0.0100 0.0005
## 20 0.0347 nan 0.0100 0.0004
## 40 0.0284 nan 0.0100 -0.0000
## 60 0.0235 nan 0.0100 -0.0001
## 80 0.0193 nan 0.0100 0.0002
## 100 0.0165 nan 0.0100 -0.0000
## 120 0.0141 nan 0.0100 0.0001
## 140 0.0124 nan 0.0100 0.0000
## 160 0.0110 nan 0.0100 -0.0001
## 180 0.0097 nan 0.0100 0.0000
## 200 0.0087 nan 0.0100 0.0000
##
## - Fold16: shrinkage=0.01, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold16: shrinkage=0.05, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0407 nan 0.0500 0.0023
## 2 0.0389 nan 0.0500 0.0017
## 3 0.0366 nan 0.0500 0.0010
## 4 0.0352 nan 0.0500 0.0014
## 5 0.0342 nan 0.0500 -0.0003
## 6 0.0319 nan 0.0500 0.0015
## 7 0.0307 nan 0.0500 0.0011
## 8 0.0292 nan 0.0500 0.0007
## 9 0.0274 nan 0.0500 0.0011
## 10 0.0266 nan 0.0500 0.0006
## 20 0.0168 nan 0.0500 0.0009
## 40 0.0080 nan 0.0500 -0.0000
## 60 0.0044 nan 0.0500 0.0001
## 80 0.0025 nan 0.0500 -0.0001
## 100 0.0014 nan 0.0500 -0.0000
## 120 0.0009 nan 0.0500 -0.0000
## 140 0.0005 nan 0.0500 -0.0000
## 160 0.0004 nan 0.0500 -0.0000
## 180 0.0002 nan 0.0500 0.0000
## 200 0.0001 nan 0.0500 -0.0000
##
## - Fold16: shrinkage=0.05, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold16: shrinkage=0.05, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0408 nan 0.0500 0.0030
## 2 0.0382 nan 0.0500 0.0015
## 3 0.0360 nan 0.0500 0.0016
## 4 0.0343 nan 0.0500 0.0020
## 5 0.0320 nan 0.0500 0.0023
## 6 0.0305 nan 0.0500 0.0015
## 7 0.0281 nan 0.0500 0.0012
## 8 0.0268 nan 0.0500 0.0011
## 9 0.0252 nan 0.0500 0.0013
## 10 0.0237 nan 0.0500 0.0005
## 20 0.0146 nan 0.0500 0.0007
## 40 0.0059 nan 0.0500 -0.0001
## 60 0.0033 nan 0.0500 -0.0000
## 80 0.0019 nan 0.0500 0.0000
## 100 0.0012 nan 0.0500 0.0000
## 120 0.0008 nan 0.0500 0.0000
## 140 0.0005 nan 0.0500 -0.0000
## 160 0.0003 nan 0.0500 0.0000
## 180 0.0002 nan 0.0500 -0.0000
## 200 0.0001 nan 0.0500 -0.0000
##
## - Fold16: shrinkage=0.05, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold16: shrinkage=0.05, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0415 nan 0.0500 0.0024
## 2 0.0383 nan 0.0500 0.0027
## 3 0.0363 nan 0.0500 0.0016
## 4 0.0342 nan 0.0500 0.0023
## 5 0.0321 nan 0.0500 0.0020
## 6 0.0303 nan 0.0500 0.0018
## 7 0.0286 nan 0.0500 0.0013
## 8 0.0275 nan 0.0500 0.0002
## 9 0.0264 nan 0.0500 0.0004
## 10 0.0248 nan 0.0500 0.0015
## 20 0.0153 nan 0.0500 0.0004
## 40 0.0075 nan 0.0500 0.0002
## 60 0.0043 nan 0.0500 0.0000
## 80 0.0028 nan 0.0500 -0.0000
## 100 0.0018 nan 0.0500 -0.0000
## 120 0.0011 nan 0.0500 0.0000
## 140 0.0008 nan 0.0500 0.0000
## 160 0.0006 nan 0.0500 -0.0000
## 180 0.0004 nan 0.0500 0.0000
## 200 0.0003 nan 0.0500 0.0000
##
## - Fold16: shrinkage=0.05, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold16: shrinkage=0.05, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0416 nan 0.0500 0.0010
## 2 0.0395 nan 0.0500 0.0021
## 3 0.0366 nan 0.0500 0.0029
## 4 0.0342 nan 0.0500 0.0022
## 5 0.0319 nan 0.0500 0.0025
## 6 0.0296 nan 0.0500 0.0004
## 7 0.0272 nan 0.0500 0.0018
## 8 0.0253 nan 0.0500 0.0016
## 9 0.0235 nan 0.0500 0.0016
## 10 0.0218 nan 0.0500 0.0017
## 20 0.0118 nan 0.0500 0.0001
## 40 0.0042 nan 0.0500 0.0001
## 60 0.0017 nan 0.0500 0.0000
## 80 0.0008 nan 0.0500 0.0000
## 100 0.0004 nan 0.0500 0.0000
## 120 0.0002 nan 0.0500 -0.0000
## 140 0.0001 nan 0.0500 0.0000
## 160 0.0001 nan 0.0500 -0.0000
## 180 0.0000 nan 0.0500 -0.0000
## 200 0.0000 nan 0.0500 -0.0000
##
## - Fold16: shrinkage=0.05, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold16: shrinkage=0.05, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0416 nan 0.0500 0.0009
## 2 0.0386 nan 0.0500 0.0021
## 3 0.0360 nan 0.0500 0.0013
## 4 0.0331 nan 0.0500 0.0013
## 5 0.0311 nan 0.0500 0.0021
## 6 0.0284 nan 0.0500 0.0015
## 7 0.0274 nan 0.0500 0.0008
## 8 0.0257 nan 0.0500 0.0018
## 9 0.0238 nan 0.0500 0.0004
## 10 0.0231 nan 0.0500 0.0000
## 20 0.0118 nan 0.0500 0.0005
## 40 0.0044 nan 0.0500 0.0001
## 60 0.0020 nan 0.0500 -0.0000
## 80 0.0010 nan 0.0500 -0.0000
## 100 0.0005 nan 0.0500 0.0000
## 120 0.0003 nan 0.0500 -0.0000
## 140 0.0002 nan 0.0500 0.0000
## 160 0.0001 nan 0.0500 -0.0000
## 180 0.0001 nan 0.0500 0.0000
## 200 0.0001 nan 0.0500 -0.0000
##
## - Fold16: shrinkage=0.05, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold16: shrinkage=0.05, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0414 nan 0.0500 0.0027
## 2 0.0388 nan 0.0500 0.0027
## 3 0.0372 nan 0.0500 0.0017
## 4 0.0345 nan 0.0500 0.0024
## 5 0.0328 nan 0.0500 0.0003
## 6 0.0307 nan 0.0500 0.0017
## 7 0.0290 nan 0.0500 0.0008
## 8 0.0273 nan 0.0500 0.0016
## 9 0.0254 nan 0.0500 0.0014
## 10 0.0237 nan 0.0500 0.0014
## 20 0.0153 nan 0.0500 0.0007
## 40 0.0073 nan 0.0500 0.0001
## 60 0.0050 nan 0.0500 -0.0000
## 80 0.0033 nan 0.0500 0.0001
## 100 0.0021 nan 0.0500 -0.0000
## 120 0.0015 nan 0.0500 -0.0000
## 140 0.0011 nan 0.0500 -0.0000
## 160 0.0008 nan 0.0500 -0.0000
## 180 0.0006 nan 0.0500 -0.0000
## 200 0.0005 nan 0.0500 -0.0000
##
## - Fold16: shrinkage=0.05, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold16: shrinkage=0.05, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0411 nan 0.0500 0.0020
## 2 0.0384 nan 0.0500 0.0022
## 3 0.0356 nan 0.0500 0.0022
## 4 0.0332 nan 0.0500 0.0018
## 5 0.0303 nan 0.0500 0.0019
## 6 0.0279 nan 0.0500 0.0019
## 7 0.0262 nan 0.0500 0.0012
## 8 0.0251 nan 0.0500 -0.0001
## 9 0.0234 nan 0.0500 0.0007
## 10 0.0208 nan 0.0500 0.0028
## 20 0.0123 nan 0.0500 0.0001
## 40 0.0045 nan 0.0500 -0.0000
## 60 0.0018 nan 0.0500 0.0000
## 80 0.0008 nan 0.0500 -0.0000
## 100 0.0003 nan 0.0500 -0.0000
## 120 0.0001 nan 0.0500 -0.0000
## 140 0.0001 nan 0.0500 0.0000
## 160 0.0000 nan 0.0500 -0.0000
## 180 0.0000 nan 0.0500 -0.0000
## 200 0.0000 nan 0.0500 0.0000
##
## - Fold16: shrinkage=0.05, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold16: shrinkage=0.05, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0426 nan 0.0500 0.0002
## 2 0.0401 nan 0.0500 0.0010
## 3 0.0371 nan 0.0500 0.0023
## 4 0.0341 nan 0.0500 0.0012
## 5 0.0314 nan 0.0500 0.0026
## 6 0.0294 nan 0.0500 0.0015
## 7 0.0273 nan 0.0500 0.0018
## 8 0.0257 nan 0.0500 0.0019
## 9 0.0234 nan 0.0500 0.0021
## 10 0.0215 nan 0.0500 0.0017
## 20 0.0117 nan 0.0500 0.0005
## 40 0.0047 nan 0.0500 0.0001
## 60 0.0022 nan 0.0500 -0.0000
## 80 0.0013 nan 0.0500 -0.0000
## 100 0.0008 nan 0.0500 -0.0000
## 120 0.0006 nan 0.0500 -0.0000
## 140 0.0004 nan 0.0500 -0.0000
## 160 0.0003 nan 0.0500 -0.0000
## 180 0.0002 nan 0.0500 0.0000
## 200 0.0002 nan 0.0500 -0.0000
##
## - Fold16: shrinkage=0.05, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold16: shrinkage=0.05, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0417 nan 0.0500 0.0019
## 2 0.0394 nan 0.0500 0.0025
## 3 0.0371 nan 0.0500 0.0018
## 4 0.0346 nan 0.0500 0.0018
## 5 0.0322 nan 0.0500 0.0021
## 6 0.0314 nan 0.0500 -0.0005
## 7 0.0296 nan 0.0500 0.0007
## 8 0.0280 nan 0.0500 0.0003
## 9 0.0268 nan 0.0500 0.0007
## 10 0.0245 nan 0.0500 0.0011
## 20 0.0162 nan 0.0500 0.0003
## 40 0.0087 nan 0.0500 -0.0001
## 60 0.0053 nan 0.0500 -0.0001
## 80 0.0033 nan 0.0500 0.0000
## 100 0.0022 nan 0.0500 -0.0000
## 120 0.0016 nan 0.0500 -0.0000
## 140 0.0012 nan 0.0500 -0.0000
## 160 0.0009 nan 0.0500 -0.0000
## 180 0.0007 nan 0.0500 0.0000
## 200 0.0005 nan 0.0500 -0.0000
##
## - Fold16: shrinkage=0.05, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold16: shrinkage=0.10, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0394 nan 0.1000 0.0033
## 2 0.0364 nan 0.1000 0.0009
## 3 0.0329 nan 0.1000 0.0039
## 4 0.0301 nan 0.1000 0.0025
## 5 0.0267 nan 0.1000 0.0032
## 6 0.0242 nan 0.1000 0.0024
## 7 0.0213 nan 0.1000 0.0028
## 8 0.0207 nan 0.1000 -0.0016
## 9 0.0183 nan 0.1000 0.0023
## 10 0.0166 nan 0.1000 0.0013
## 20 0.0076 nan 0.1000 0.0008
## 40 0.0022 nan 0.1000 -0.0000
## 60 0.0007 nan 0.1000 0.0000
## 80 0.0003 nan 0.1000 -0.0000
## 100 0.0001 nan 0.1000 -0.0000
## 120 0.0001 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold16: shrinkage=0.10, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold16: shrinkage=0.10, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0392 nan 0.1000 0.0025
## 2 0.0337 nan 0.1000 0.0046
## 3 0.0301 nan 0.1000 0.0020
## 4 0.0268 nan 0.1000 0.0034
## 5 0.0247 nan 0.1000 0.0020
## 6 0.0227 nan 0.1000 0.0022
## 7 0.0214 nan 0.1000 -0.0008
## 8 0.0186 nan 0.1000 0.0017
## 9 0.0173 nan 0.1000 0.0008
## 10 0.0164 nan 0.1000 0.0007
## 20 0.0070 nan 0.1000 -0.0001
## 40 0.0024 nan 0.1000 -0.0000
## 60 0.0008 nan 0.1000 0.0001
## 80 0.0003 nan 0.1000 -0.0000
## 100 0.0001 nan 0.1000 -0.0000
## 120 0.0001 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold16: shrinkage=0.10, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold16: shrinkage=0.10, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0418 nan 0.1000 -0.0008
## 2 0.0369 nan 0.1000 0.0033
## 3 0.0317 nan 0.1000 0.0020
## 4 0.0293 nan 0.1000 0.0018
## 5 0.0272 nan 0.1000 -0.0006
## 6 0.0235 nan 0.1000 0.0018
## 7 0.0207 nan 0.1000 0.0023
## 8 0.0188 nan 0.1000 0.0001
## 9 0.0168 nan 0.1000 0.0012
## 10 0.0152 nan 0.1000 0.0006
## 20 0.0072 nan 0.1000 -0.0002
## 40 0.0032 nan 0.1000 0.0001
## 60 0.0019 nan 0.1000 -0.0000
## 80 0.0012 nan 0.1000 -0.0001
## 100 0.0007 nan 0.1000 -0.0000
## 120 0.0004 nan 0.1000 -0.0000
## 140 0.0002 nan 0.1000 -0.0000
## 160 0.0001 nan 0.1000 -0.0000
## 180 0.0001 nan 0.1000 -0.0000
## 200 0.0001 nan 0.1000 -0.0000
##
## - Fold16: shrinkage=0.10, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold16: shrinkage=0.10, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0376 nan 0.1000 0.0031
## 2 0.0321 nan 0.1000 0.0031
## 3 0.0276 nan 0.1000 0.0026
## 4 0.0247 nan 0.1000 0.0008
## 5 0.0216 nan 0.1000 0.0018
## 6 0.0188 nan 0.1000 0.0023
## 7 0.0173 nan 0.1000 0.0004
## 8 0.0144 nan 0.1000 0.0021
## 9 0.0138 nan 0.1000 -0.0002
## 10 0.0128 nan 0.1000 0.0001
## 20 0.0038 nan 0.1000 0.0007
## 40 0.0006 nan 0.1000 0.0000
## 60 0.0001 nan 0.1000 -0.0000
## 80 0.0000 nan 0.1000 -0.0000
## 100 0.0000 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold16: shrinkage=0.10, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold16: shrinkage=0.10, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0375 nan 0.1000 0.0066
## 2 0.0315 nan 0.1000 0.0052
## 3 0.0284 nan 0.1000 0.0027
## 4 0.0260 nan 0.1000 0.0007
## 5 0.0222 nan 0.1000 0.0016
## 6 0.0195 nan 0.1000 0.0026
## 7 0.0175 nan 0.1000 0.0014
## 8 0.0152 nan 0.1000 0.0015
## 9 0.0140 nan 0.1000 0.0009
## 10 0.0129 nan 0.1000 0.0009
## 20 0.0045 nan 0.1000 0.0003
## 40 0.0009 nan 0.1000 -0.0000
## 60 0.0003 nan 0.1000 0.0000
## 80 0.0001 nan 0.1000 -0.0000
## 100 0.0001 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold16: shrinkage=0.10, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold16: shrinkage=0.10, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0386 nan 0.1000 0.0057
## 2 0.0350 nan 0.1000 0.0038
## 3 0.0325 nan 0.1000 0.0008
## 4 0.0296 nan 0.1000 0.0025
## 5 0.0262 nan 0.1000 0.0024
## 6 0.0233 nan 0.1000 0.0020
## 7 0.0215 nan 0.1000 0.0017
## 8 0.0197 nan 0.1000 0.0014
## 9 0.0189 nan 0.1000 -0.0012
## 10 0.0174 nan 0.1000 0.0011
## 20 0.0098 nan 0.1000 -0.0002
## 40 0.0036 nan 0.1000 0.0001
## 60 0.0018 nan 0.1000 -0.0001
## 80 0.0011 nan 0.1000 0.0000
## 100 0.0007 nan 0.1000 -0.0000
## 120 0.0004 nan 0.1000 -0.0000
## 140 0.0002 nan 0.1000 -0.0000
## 160 0.0002 nan 0.1000 0.0000
## 180 0.0001 nan 0.1000 -0.0000
## 200 0.0001 nan 0.1000 -0.0000
##
## - Fold16: shrinkage=0.10, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold16: shrinkage=0.10, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0386 nan 0.1000 0.0035
## 2 0.0316 nan 0.1000 0.0038
## 3 0.0269 nan 0.1000 0.0035
## 4 0.0250 nan 0.1000 0.0011
## 5 0.0221 nan 0.1000 0.0018
## 6 0.0188 nan 0.1000 0.0015
## 7 0.0158 nan 0.1000 0.0010
## 8 0.0138 nan 0.1000 0.0021
## 9 0.0119 nan 0.1000 0.0010
## 10 0.0110 nan 0.1000 0.0002
## 20 0.0041 nan 0.1000 0.0002
## 40 0.0006 nan 0.1000 0.0000
## 60 0.0001 nan 0.1000 0.0000
## 80 0.0000 nan 0.1000 -0.0000
## 100 0.0000 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 0.0000
##
## - Fold16: shrinkage=0.10, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold16: shrinkage=0.10, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0393 nan 0.1000 0.0037
## 2 0.0325 nan 0.1000 0.0060
## 3 0.0276 nan 0.1000 0.0022
## 4 0.0246 nan 0.1000 0.0026
## 5 0.0209 nan 0.1000 0.0028
## 6 0.0179 nan 0.1000 0.0026
## 7 0.0161 nan 0.1000 0.0013
## 8 0.0141 nan 0.1000 0.0018
## 9 0.0124 nan 0.1000 0.0015
## 10 0.0114 nan 0.1000 0.0003
## 20 0.0042 nan 0.1000 -0.0001
## 40 0.0011 nan 0.1000 -0.0000
## 60 0.0004 nan 0.1000 -0.0000
## 80 0.0001 nan 0.1000 -0.0000
## 100 0.0001 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 0.0000
## 140 0.0000 nan 0.1000 0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold16: shrinkage=0.10, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold16: shrinkage=0.10, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0381 nan 0.1000 0.0059
## 2 0.0348 nan 0.1000 0.0009
## 3 0.0334 nan 0.1000 -0.0007
## 4 0.0308 nan 0.1000 -0.0002
## 5 0.0270 nan 0.1000 0.0027
## 6 0.0259 nan 0.1000 -0.0009
## 7 0.0256 nan 0.1000 -0.0009
## 8 0.0234 nan 0.1000 0.0007
## 9 0.0204 nan 0.1000 0.0017
## 10 0.0190 nan 0.1000 0.0005
## 20 0.0099 nan 0.1000 0.0008
## 40 0.0036 nan 0.1000 -0.0001
## 60 0.0019 nan 0.1000 0.0000
## 80 0.0012 nan 0.1000 -0.0001
## 100 0.0007 nan 0.1000 0.0000
## 120 0.0005 nan 0.1000 -0.0000
## 140 0.0003 nan 0.1000 0.0000
## 160 0.0002 nan 0.1000 -0.0000
## 180 0.0002 nan 0.1000 -0.0000
## 200 0.0001 nan 0.1000 -0.0000
##
## - Fold16: shrinkage=0.10, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold17: shrinkage=0.01, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0433 nan 0.0100 0.0007
## 2 0.0427 nan 0.0100 0.0006
## 3 0.0421 nan 0.0100 0.0004
## 4 0.0417 nan 0.0100 0.0002
## 5 0.0412 nan 0.0100 0.0005
## 6 0.0408 nan 0.0100 0.0005
## 7 0.0404 nan 0.0100 0.0004
## 8 0.0398 nan 0.0100 0.0005
## 9 0.0393 nan 0.0100 0.0005
## 10 0.0388 nan 0.0100 0.0004
## 20 0.0343 nan 0.0100 0.0003
## 40 0.0269 nan 0.0100 0.0003
## 60 0.0214 nan 0.0100 0.0002
## 80 0.0174 nan 0.0100 0.0002
## 100 0.0139 nan 0.0100 0.0001
## 120 0.0115 nan 0.0100 0.0001
## 140 0.0099 nan 0.0100 0.0001
## 160 0.0081 nan 0.0100 0.0001
## 180 0.0069 nan 0.0100 0.0001
## 200 0.0057 nan 0.0100 0.0000
##
## - Fold17: shrinkage=0.01, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold17: shrinkage=0.01, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0431 nan 0.0100 0.0006
## 2 0.0426 nan 0.0100 0.0005
## 3 0.0422 nan 0.0100 0.0001
## 4 0.0418 nan 0.0100 0.0004
## 5 0.0415 nan 0.0100 0.0001
## 6 0.0409 nan 0.0100 0.0006
## 7 0.0405 nan 0.0100 0.0003
## 8 0.0400 nan 0.0100 0.0005
## 9 0.0394 nan 0.0100 0.0005
## 10 0.0387 nan 0.0100 0.0006
## 20 0.0341 nan 0.0100 0.0004
## 40 0.0275 nan 0.0100 -0.0000
## 60 0.0224 nan 0.0100 0.0001
## 80 0.0182 nan 0.0100 0.0002
## 100 0.0150 nan 0.0100 0.0001
## 120 0.0126 nan 0.0100 0.0001
## 140 0.0103 nan 0.0100 0.0000
## 160 0.0088 nan 0.0100 0.0000
## 180 0.0073 nan 0.0100 0.0000
## 200 0.0062 nan 0.0100 0.0000
##
## - Fold17: shrinkage=0.01, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold17: shrinkage=0.01, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0434 nan 0.0100 0.0006
## 2 0.0429 nan 0.0100 0.0006
## 3 0.0424 nan 0.0100 0.0001
## 4 0.0420 nan 0.0100 0.0001
## 5 0.0414 nan 0.0100 0.0005
## 6 0.0412 nan 0.0100 0.0001
## 7 0.0406 nan 0.0100 0.0004
## 8 0.0401 nan 0.0100 0.0005
## 9 0.0396 nan 0.0100 0.0004
## 10 0.0391 nan 0.0100 0.0001
## 20 0.0351 nan 0.0100 0.0005
## 40 0.0280 nan 0.0100 0.0001
## 60 0.0226 nan 0.0100 0.0000
## 80 0.0186 nan 0.0100 0.0001
## 100 0.0155 nan 0.0100 0.0001
## 120 0.0133 nan 0.0100 0.0001
## 140 0.0116 nan 0.0100 0.0000
## 160 0.0101 nan 0.0100 -0.0001
## 180 0.0090 nan 0.0100 0.0000
## 200 0.0082 nan 0.0100 -0.0001
##
## - Fold17: shrinkage=0.01, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold17: shrinkage=0.01, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0432 nan 0.0100 0.0004
## 2 0.0428 nan 0.0100 0.0003
## 3 0.0421 nan 0.0100 0.0004
## 4 0.0416 nan 0.0100 0.0004
## 5 0.0409 nan 0.0100 0.0005
## 6 0.0404 nan 0.0100 0.0004
## 7 0.0397 nan 0.0100 0.0005
## 8 0.0390 nan 0.0100 0.0006
## 9 0.0384 nan 0.0100 0.0004
## 10 0.0379 nan 0.0100 0.0006
## 20 0.0330 nan 0.0100 0.0003
## 40 0.0250 nan 0.0100 0.0005
## 60 0.0188 nan 0.0100 0.0002
## 80 0.0143 nan 0.0100 0.0001
## 100 0.0113 nan 0.0100 0.0002
## 120 0.0092 nan 0.0100 0.0000
## 140 0.0074 nan 0.0100 -0.0000
## 160 0.0059 nan 0.0100 0.0001
## 180 0.0048 nan 0.0100 0.0001
## 200 0.0039 nan 0.0100 0.0000
##
## - Fold17: shrinkage=0.01, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold17: shrinkage=0.01, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0431 nan 0.0100 0.0005
## 2 0.0425 nan 0.0100 0.0004
## 3 0.0418 nan 0.0100 0.0004
## 4 0.0414 nan 0.0100 0.0001
## 5 0.0408 nan 0.0100 0.0006
## 6 0.0402 nan 0.0100 0.0006
## 7 0.0396 nan 0.0100 0.0004
## 8 0.0390 nan 0.0100 0.0004
## 9 0.0386 nan 0.0100 0.0004
## 10 0.0380 nan 0.0100 0.0005
## 20 0.0329 nan 0.0100 0.0002
## 40 0.0249 nan 0.0100 0.0003
## 60 0.0195 nan 0.0100 0.0002
## 80 0.0150 nan 0.0100 0.0000
## 100 0.0118 nan 0.0100 0.0002
## 120 0.0093 nan 0.0100 0.0001
## 140 0.0073 nan 0.0100 0.0001
## 160 0.0058 nan 0.0100 0.0001
## 180 0.0048 nan 0.0100 -0.0000
## 200 0.0039 nan 0.0100 0.0000
##
## - Fold17: shrinkage=0.01, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold17: shrinkage=0.01, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0433 nan 0.0100 0.0006
## 2 0.0427 nan 0.0100 0.0004
## 3 0.0424 nan 0.0100 0.0002
## 4 0.0418 nan 0.0100 0.0005
## 5 0.0413 nan 0.0100 0.0004
## 6 0.0408 nan 0.0100 0.0006
## 7 0.0402 nan 0.0100 0.0005
## 8 0.0397 nan 0.0100 0.0005
## 9 0.0394 nan 0.0100 0.0001
## 10 0.0391 nan 0.0100 0.0003
## 20 0.0345 nan 0.0100 0.0003
## 40 0.0279 nan 0.0100 0.0003
## 60 0.0233 nan 0.0100 0.0001
## 80 0.0192 nan 0.0100 0.0002
## 100 0.0160 nan 0.0100 -0.0000
## 120 0.0137 nan 0.0100 0.0001
## 140 0.0121 nan 0.0100 0.0001
## 160 0.0105 nan 0.0100 -0.0000
## 180 0.0093 nan 0.0100 0.0000
## 200 0.0083 nan 0.0100 0.0000
##
## - Fold17: shrinkage=0.01, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold17: shrinkage=0.01, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0437 nan 0.0100 -0.0000
## 2 0.0432 nan 0.0100 0.0005
## 3 0.0429 nan 0.0100 0.0003
## 4 0.0424 nan 0.0100 0.0001
## 5 0.0418 nan 0.0100 0.0004
## 6 0.0411 nan 0.0100 0.0003
## 7 0.0404 nan 0.0100 0.0008
## 8 0.0398 nan 0.0100 0.0006
## 9 0.0390 nan 0.0100 0.0007
## 10 0.0383 nan 0.0100 0.0006
## 20 0.0333 nan 0.0100 0.0005
## 40 0.0253 nan 0.0100 0.0001
## 60 0.0184 nan 0.0100 0.0004
## 80 0.0138 nan 0.0100 0.0001
## 100 0.0105 nan 0.0100 -0.0001
## 120 0.0081 nan 0.0100 0.0001
## 140 0.0064 nan 0.0100 0.0001
## 160 0.0050 nan 0.0100 0.0000
## 180 0.0039 nan 0.0100 0.0000
## 200 0.0031 nan 0.0100 0.0000
##
## - Fold17: shrinkage=0.01, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold17: shrinkage=0.01, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0433 nan 0.0100 0.0005
## 2 0.0428 nan 0.0100 0.0001
## 3 0.0423 nan 0.0100 0.0004
## 4 0.0416 nan 0.0100 0.0002
## 5 0.0410 nan 0.0100 0.0003
## 6 0.0405 nan 0.0100 0.0002
## 7 0.0398 nan 0.0100 0.0006
## 8 0.0391 nan 0.0100 0.0006
## 9 0.0386 nan 0.0100 0.0006
## 10 0.0380 nan 0.0100 0.0003
## 20 0.0332 nan 0.0100 0.0001
## 40 0.0251 nan 0.0100 0.0004
## 60 0.0194 nan 0.0100 0.0001
## 80 0.0147 nan 0.0100 0.0002
## 100 0.0110 nan 0.0100 0.0001
## 120 0.0088 nan 0.0100 0.0000
## 140 0.0073 nan 0.0100 -0.0000
## 160 0.0059 nan 0.0100 0.0000
## 180 0.0047 nan 0.0100 0.0000
## 200 0.0039 nan 0.0100 0.0000
##
## - Fold17: shrinkage=0.01, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold17: shrinkage=0.01, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0433 nan 0.0100 0.0005
## 2 0.0427 nan 0.0100 0.0006
## 3 0.0422 nan 0.0100 0.0003
## 4 0.0416 nan 0.0100 0.0006
## 5 0.0412 nan 0.0100 0.0003
## 6 0.0408 nan 0.0100 0.0002
## 7 0.0403 nan 0.0100 0.0006
## 8 0.0400 nan 0.0100 0.0001
## 9 0.0394 nan 0.0100 0.0005
## 10 0.0389 nan 0.0100 0.0005
## 20 0.0349 nan 0.0100 0.0004
## 40 0.0279 nan 0.0100 0.0001
## 60 0.0223 nan 0.0100 0.0002
## 80 0.0182 nan 0.0100 0.0001
## 100 0.0154 nan 0.0100 0.0000
## 120 0.0129 nan 0.0100 0.0001
## 140 0.0110 nan 0.0100 0.0000
## 160 0.0096 nan 0.0100 0.0000
## 180 0.0087 nan 0.0100 0.0001
## 200 0.0076 nan 0.0100 0.0000
##
## - Fold17: shrinkage=0.01, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold17: shrinkage=0.05, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0419 nan 0.0500 0.0017
## 2 0.0389 nan 0.0500 0.0018
## 3 0.0365 nan 0.0500 0.0024
## 4 0.0348 nan 0.0500 0.0016
## 5 0.0342 nan 0.0500 0.0000
## 6 0.0325 nan 0.0500 0.0014
## 7 0.0309 nan 0.0500 0.0010
## 8 0.0286 nan 0.0500 0.0020
## 9 0.0274 nan 0.0500 0.0006
## 10 0.0262 nan 0.0500 0.0008
## 20 0.0140 nan 0.0500 0.0006
## 40 0.0058 nan 0.0500 0.0002
## 60 0.0026 nan 0.0500 0.0001
## 80 0.0014 nan 0.0500 0.0000
## 100 0.0008 nan 0.0500 0.0000
## 120 0.0005 nan 0.0500 0.0000
## 140 0.0003 nan 0.0500 0.0000
## 160 0.0002 nan 0.0500 0.0000
## 180 0.0001 nan 0.0500 -0.0000
## 200 0.0001 nan 0.0500 -0.0000
##
## - Fold17: shrinkage=0.05, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold17: shrinkage=0.05, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0415 nan 0.0500 0.0023
## 2 0.0384 nan 0.0500 0.0022
## 3 0.0366 nan 0.0500 0.0008
## 4 0.0353 nan 0.0500 0.0005
## 5 0.0349 nan 0.0500 -0.0022
## 6 0.0330 nan 0.0500 0.0019
## 7 0.0304 nan 0.0500 0.0024
## 8 0.0291 nan 0.0500 0.0013
## 9 0.0268 nan 0.0500 0.0018
## 10 0.0253 nan 0.0500 0.0012
## 20 0.0145 nan 0.0500 0.0005
## 40 0.0065 nan 0.0500 0.0003
## 60 0.0027 nan 0.0500 0.0001
## 80 0.0017 nan 0.0500 -0.0000
## 100 0.0010 nan 0.0500 0.0000
## 120 0.0007 nan 0.0500 0.0000
## 140 0.0004 nan 0.0500 -0.0000
## 160 0.0003 nan 0.0500 0.0000
## 180 0.0002 nan 0.0500 -0.0000
## 200 0.0001 nan 0.0500 0.0000
##
## - Fold17: shrinkage=0.05, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold17: shrinkage=0.05, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0401 nan 0.0500 0.0025
## 2 0.0376 nan 0.0500 0.0025
## 3 0.0355 nan 0.0500 0.0021
## 4 0.0337 nan 0.0500 0.0014
## 5 0.0320 nan 0.0500 0.0016
## 6 0.0306 nan 0.0500 0.0016
## 7 0.0299 nan 0.0500 0.0001
## 8 0.0283 nan 0.0500 0.0016
## 9 0.0270 nan 0.0500 0.0010
## 10 0.0256 nan 0.0500 0.0014
## 20 0.0164 nan 0.0500 0.0003
## 40 0.0081 nan 0.0500 0.0002
## 60 0.0047 nan 0.0500 0.0001
## 80 0.0035 nan 0.0500 -0.0000
## 100 0.0024 nan 0.0500 0.0000
## 120 0.0016 nan 0.0500 -0.0000
## 140 0.0011 nan 0.0500 0.0000
## 160 0.0008 nan 0.0500 0.0000
## 180 0.0006 nan 0.0500 -0.0000
## 200 0.0005 nan 0.0500 0.0000
##
## - Fold17: shrinkage=0.05, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold17: shrinkage=0.05, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0404 nan 0.0500 0.0039
## 2 0.0384 nan 0.0500 0.0016
## 3 0.0366 nan 0.0500 0.0019
## 4 0.0339 nan 0.0500 0.0026
## 5 0.0316 nan 0.0500 0.0017
## 6 0.0299 nan 0.0500 0.0003
## 7 0.0289 nan 0.0500 -0.0000
## 8 0.0276 nan 0.0500 0.0012
## 9 0.0255 nan 0.0500 0.0013
## 10 0.0232 nan 0.0500 0.0017
## 20 0.0138 nan 0.0500 0.0005
## 40 0.0039 nan 0.0500 0.0002
## 60 0.0017 nan 0.0500 0.0000
## 80 0.0008 nan 0.0500 -0.0000
## 100 0.0004 nan 0.0500 -0.0000
## 120 0.0002 nan 0.0500 -0.0000
## 140 0.0001 nan 0.0500 -0.0000
## 160 0.0000 nan 0.0500 0.0000
## 180 0.0000 nan 0.0500 -0.0000
## 200 0.0000 nan 0.0500 0.0000
##
## - Fold17: shrinkage=0.05, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold17: shrinkage=0.05, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0402 nan 0.0500 0.0041
## 2 0.0377 nan 0.0500 0.0024
## 3 0.0362 nan 0.0500 0.0013
## 4 0.0344 nan 0.0500 0.0010
## 5 0.0315 nan 0.0500 0.0024
## 6 0.0293 nan 0.0500 0.0022
## 7 0.0278 nan 0.0500 0.0005
## 8 0.0264 nan 0.0500 0.0014
## 9 0.0239 nan 0.0500 0.0017
## 10 0.0221 nan 0.0500 0.0015
## 20 0.0114 nan 0.0500 0.0007
## 40 0.0039 nan 0.0500 0.0002
## 60 0.0017 nan 0.0500 0.0001
## 80 0.0010 nan 0.0500 -0.0000
## 100 0.0006 nan 0.0500 -0.0000
## 120 0.0003 nan 0.0500 0.0000
## 140 0.0002 nan 0.0500 0.0000
## 160 0.0001 nan 0.0500 0.0000
## 180 0.0001 nan 0.0500 0.0000
## 200 0.0001 nan 0.0500 -0.0000
##
## - Fold17: shrinkage=0.05, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold17: shrinkage=0.05, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0405 nan 0.0500 0.0026
## 2 0.0376 nan 0.0500 0.0024
## 3 0.0350 nan 0.0500 0.0024
## 4 0.0333 nan 0.0500 0.0003
## 5 0.0312 nan 0.0500 0.0016
## 6 0.0302 nan 0.0500 0.0003
## 7 0.0280 nan 0.0500 0.0014
## 8 0.0263 nan 0.0500 0.0016
## 9 0.0254 nan 0.0500 0.0009
## 10 0.0250 nan 0.0500 0.0001
## 20 0.0157 nan 0.0500 0.0006
## 40 0.0092 nan 0.0500 -0.0001
## 60 0.0053 nan 0.0500 0.0001
## 80 0.0034 nan 0.0500 -0.0000
## 100 0.0022 nan 0.0500 0.0000
## 120 0.0014 nan 0.0500 0.0000
## 140 0.0010 nan 0.0500 -0.0000
## 160 0.0008 nan 0.0500 -0.0000
## 180 0.0006 nan 0.0500 -0.0000
## 200 0.0005 nan 0.0500 0.0000
##
## - Fold17: shrinkage=0.05, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold17: shrinkage=0.05, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0400 nan 0.0500 0.0029
## 2 0.0372 nan 0.0500 0.0034
## 3 0.0348 nan 0.0500 0.0017
## 4 0.0333 nan 0.0500 0.0006
## 5 0.0310 nan 0.0500 0.0014
## 6 0.0290 nan 0.0500 0.0016
## 7 0.0272 nan 0.0500 0.0008
## 8 0.0256 nan 0.0500 0.0012
## 9 0.0233 nan 0.0500 0.0021
## 10 0.0221 nan 0.0500 0.0011
## 20 0.0103 nan 0.0500 0.0006
## 40 0.0030 nan 0.0500 -0.0000
## 60 0.0009 nan 0.0500 -0.0000
## 80 0.0004 nan 0.0500 0.0000
## 100 0.0002 nan 0.0500 -0.0000
## 120 0.0001 nan 0.0500 0.0000
## 140 0.0000 nan 0.0500 0.0000
## 160 0.0000 nan 0.0500 0.0000
## 180 0.0000 nan 0.0500 0.0000
## 200 0.0000 nan 0.0500 -0.0000
##
## - Fold17: shrinkage=0.05, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold17: shrinkage=0.05, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0419 nan 0.0500 0.0001
## 2 0.0384 nan 0.0500 0.0030
## 3 0.0374 nan 0.0500 -0.0001
## 4 0.0340 nan 0.0500 0.0018
## 5 0.0325 nan 0.0500 0.0010
## 6 0.0313 nan 0.0500 0.0008
## 7 0.0287 nan 0.0500 0.0012
## 8 0.0269 nan 0.0500 0.0014
## 9 0.0244 nan 0.0500 0.0021
## 10 0.0226 nan 0.0500 0.0016
## 20 0.0104 nan 0.0500 0.0007
## 40 0.0034 nan 0.0500 -0.0000
## 60 0.0015 nan 0.0500 0.0000
## 80 0.0007 nan 0.0500 0.0000
## 100 0.0004 nan 0.0500 -0.0000
## 120 0.0002 nan 0.0500 0.0000
## 140 0.0001 nan 0.0500 -0.0000
## 160 0.0001 nan 0.0500 -0.0000
## 180 0.0001 nan 0.0500 -0.0000
## 200 0.0000 nan 0.0500 -0.0000
##
## - Fold17: shrinkage=0.05, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold17: shrinkage=0.05, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0416 nan 0.0500 0.0019
## 2 0.0394 nan 0.0500 0.0027
## 3 0.0360 nan 0.0500 0.0023
## 4 0.0338 nan 0.0500 0.0018
## 5 0.0314 nan 0.0500 0.0018
## 6 0.0295 nan 0.0500 0.0020
## 7 0.0280 nan 0.0500 0.0014
## 8 0.0261 nan 0.0500 0.0014
## 9 0.0248 nan 0.0500 0.0010
## 10 0.0240 nan 0.0500 0.0005
## 20 0.0160 nan 0.0500 0.0005
## 40 0.0085 nan 0.0500 0.0002
## 60 0.0054 nan 0.0500 -0.0000
## 80 0.0036 nan 0.0500 -0.0000
## 100 0.0025 nan 0.0500 -0.0000
## 120 0.0019 nan 0.0500 -0.0001
## 140 0.0014 nan 0.0500 -0.0000
## 160 0.0010 nan 0.0500 -0.0000
## 180 0.0008 nan 0.0500 -0.0000
## 200 0.0006 nan 0.0500 -0.0000
##
## - Fold17: shrinkage=0.05, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold17: shrinkage=0.10, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0383 nan 0.1000 0.0051
## 2 0.0333 nan 0.1000 0.0036
## 3 0.0306 nan 0.1000 0.0025
## 4 0.0255 nan 0.1000 0.0022
## 5 0.0221 nan 0.1000 0.0005
## 6 0.0197 nan 0.1000 0.0022
## 7 0.0172 nan 0.1000 0.0016
## 8 0.0151 nan 0.1000 0.0010
## 9 0.0134 nan 0.1000 0.0015
## 10 0.0126 nan 0.1000 0.0007
## 20 0.0053 nan 0.1000 0.0001
## 40 0.0011 nan 0.1000 0.0000
## 60 0.0004 nan 0.1000 0.0000
## 80 0.0001 nan 0.1000 0.0000
## 100 0.0001 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold17: shrinkage=0.10, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold17: shrinkage=0.10, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0379 nan 0.1000 0.0053
## 2 0.0342 nan 0.1000 0.0025
## 3 0.0306 nan 0.1000 0.0032
## 4 0.0260 nan 0.1000 0.0029
## 5 0.0222 nan 0.1000 0.0036
## 6 0.0199 nan 0.1000 0.0016
## 7 0.0179 nan 0.1000 0.0019
## 8 0.0160 nan 0.1000 0.0009
## 9 0.0142 nan 0.1000 0.0014
## 10 0.0128 nan 0.1000 0.0008
## 20 0.0059 nan 0.1000 0.0002
## 40 0.0015 nan 0.1000 0.0000
## 60 0.0006 nan 0.1000 -0.0000
## 80 0.0002 nan 0.1000 -0.0000
## 100 0.0001 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 0.0000
## 160 0.0000 nan 0.1000 0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold17: shrinkage=0.10, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold17: shrinkage=0.10, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0377 nan 0.1000 0.0057
## 2 0.0330 nan 0.1000 0.0044
## 3 0.0298 nan 0.1000 0.0034
## 4 0.0267 nan 0.1000 0.0030
## 5 0.0231 nan 0.1000 0.0020
## 6 0.0213 nan 0.1000 0.0016
## 7 0.0203 nan 0.1000 -0.0006
## 8 0.0175 nan 0.1000 0.0005
## 9 0.0162 nan 0.1000 0.0010
## 10 0.0156 nan 0.1000 0.0005
## 20 0.0081 nan 0.1000 -0.0002
## 40 0.0035 nan 0.1000 -0.0002
## 60 0.0019 nan 0.1000 -0.0001
## 80 0.0010 nan 0.1000 -0.0000
## 100 0.0005 nan 0.1000 -0.0000
## 120 0.0003 nan 0.1000 -0.0000
## 140 0.0002 nan 0.1000 -0.0000
## 160 0.0002 nan 0.1000 -0.0000
## 180 0.0001 nan 0.1000 -0.0000
## 200 0.0001 nan 0.1000 0.0000
##
## - Fold17: shrinkage=0.10, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold17: shrinkage=0.10, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0381 nan 0.1000 0.0039
## 2 0.0338 nan 0.1000 0.0042
## 3 0.0306 nan 0.1000 0.0012
## 4 0.0262 nan 0.1000 0.0046
## 5 0.0225 nan 0.1000 0.0030
## 6 0.0188 nan 0.1000 0.0028
## 7 0.0168 nan 0.1000 0.0014
## 8 0.0150 nan 0.1000 0.0011
## 9 0.0128 nan 0.1000 0.0016
## 10 0.0120 nan 0.1000 0.0003
## 20 0.0047 nan 0.1000 0.0001
## 40 0.0010 nan 0.1000 0.0001
## 60 0.0002 nan 0.1000 0.0000
## 80 0.0001 nan 0.1000 -0.0000
## 100 0.0000 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold17: shrinkage=0.10, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold17: shrinkage=0.10, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0377 nan 0.1000 0.0060
## 2 0.0323 nan 0.1000 0.0023
## 3 0.0280 nan 0.1000 0.0038
## 4 0.0240 nan 0.1000 0.0028
## 5 0.0213 nan 0.1000 0.0015
## 6 0.0192 nan 0.1000 0.0019
## 7 0.0164 nan 0.1000 0.0025
## 8 0.0151 nan 0.1000 0.0007
## 9 0.0139 nan 0.1000 0.0003
## 10 0.0122 nan 0.1000 0.0012
## 20 0.0041 nan 0.1000 0.0001
## 40 0.0010 nan 0.1000 0.0000
## 60 0.0003 nan 0.1000 -0.0000
## 80 0.0001 nan 0.1000 -0.0000
## 100 0.0001 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold17: shrinkage=0.10, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold17: shrinkage=0.10, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0376 nan 0.1000 0.0057
## 2 0.0343 nan 0.1000 0.0028
## 3 0.0301 nan 0.1000 0.0017
## 4 0.0263 nan 0.1000 0.0038
## 5 0.0231 nan 0.1000 0.0023
## 6 0.0205 nan 0.1000 0.0018
## 7 0.0188 nan 0.1000 0.0016
## 8 0.0163 nan 0.1000 0.0006
## 9 0.0151 nan 0.1000 0.0012
## 10 0.0142 nan 0.1000 0.0002
## 20 0.0072 nan 0.1000 0.0003
## 40 0.0036 nan 0.1000 0.0001
## 60 0.0015 nan 0.1000 -0.0002
## 80 0.0007 nan 0.1000 -0.0000
## 100 0.0004 nan 0.1000 -0.0000
## 120 0.0003 nan 0.1000 -0.0000
## 140 0.0002 nan 0.1000 -0.0000
## 160 0.0001 nan 0.1000 -0.0000
## 180 0.0001 nan 0.1000 0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold17: shrinkage=0.10, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold17: shrinkage=0.10, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0384 nan 0.1000 0.0032
## 2 0.0329 nan 0.1000 0.0058
## 3 0.0306 nan 0.1000 0.0017
## 4 0.0247 nan 0.1000 0.0027
## 5 0.0213 nan 0.1000 0.0023
## 6 0.0180 nan 0.1000 0.0030
## 7 0.0161 nan 0.1000 0.0019
## 8 0.0142 nan 0.1000 0.0009
## 9 0.0123 nan 0.1000 -0.0003
## 10 0.0105 nan 0.1000 0.0011
## 20 0.0033 nan 0.1000 0.0002
## 40 0.0006 nan 0.1000 0.0000
## 60 0.0001 nan 0.1000 0.0000
## 80 0.0000 nan 0.1000 0.0000
## 100 0.0000 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold17: shrinkage=0.10, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold17: shrinkage=0.10, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0379 nan 0.1000 0.0056
## 2 0.0315 nan 0.1000 0.0032
## 3 0.0285 nan 0.1000 0.0031
## 4 0.0234 nan 0.1000 0.0045
## 5 0.0209 nan 0.1000 0.0024
## 6 0.0190 nan 0.1000 0.0020
## 7 0.0161 nan 0.1000 0.0024
## 8 0.0136 nan 0.1000 0.0018
## 9 0.0114 nan 0.1000 0.0016
## 10 0.0098 nan 0.1000 0.0014
## 20 0.0028 nan 0.1000 0.0000
## 40 0.0006 nan 0.1000 -0.0001
## 60 0.0002 nan 0.1000 0.0000
## 80 0.0001 nan 0.1000 -0.0000
## 100 0.0000 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold17: shrinkage=0.10, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold17: shrinkage=0.10, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0374 nan 0.1000 0.0052
## 2 0.0325 nan 0.1000 0.0041
## 3 0.0284 nan 0.1000 0.0023
## 4 0.0251 nan 0.1000 0.0033
## 5 0.0229 nan 0.1000 0.0025
## 6 0.0208 nan 0.1000 0.0021
## 7 0.0195 nan 0.1000 0.0013
## 8 0.0172 nan 0.1000 0.0019
## 9 0.0157 nan 0.1000 0.0016
## 10 0.0149 nan 0.1000 0.0002
## 20 0.0086 nan 0.1000 -0.0005
## 40 0.0034 nan 0.1000 -0.0001
## 60 0.0018 nan 0.1000 -0.0001
## 80 0.0009 nan 0.1000 -0.0000
## 100 0.0006 nan 0.1000 -0.0000
## 120 0.0004 nan 0.1000 -0.0000
## 140 0.0003 nan 0.1000 -0.0000
## 160 0.0002 nan 0.1000 0.0000
## 180 0.0001 nan 0.1000 0.0000
## 200 0.0001 nan 0.1000 0.0000
##
## - Fold17: shrinkage=0.10, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold18: shrinkage=0.01, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0430 nan 0.0100 0.0002
## 2 0.0424 nan 0.0100 0.0005
## 3 0.0421 nan 0.0100 0.0001
## 4 0.0415 nan 0.0100 0.0002
## 5 0.0410 nan 0.0100 0.0005
## 6 0.0405 nan 0.0100 0.0005
## 7 0.0400 nan 0.0100 0.0005
## 8 0.0395 nan 0.0100 0.0002
## 9 0.0389 nan 0.0100 0.0005
## 10 0.0385 nan 0.0100 0.0002
## 20 0.0345 nan 0.0100 0.0003
## 40 0.0270 nan 0.0100 0.0003
## 60 0.0224 nan 0.0100 0.0002
## 80 0.0178 nan 0.0100 -0.0001
## 100 0.0144 nan 0.0100 0.0001
## 120 0.0119 nan 0.0100 0.0001
## 140 0.0098 nan 0.0100 0.0001
## 160 0.0082 nan 0.0100 0.0001
## 180 0.0069 nan 0.0100 0.0001
## 200 0.0057 nan 0.0100 0.0000
##
## - Fold18: shrinkage=0.01, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold18: shrinkage=0.01, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0428 nan 0.0100 0.0005
## 2 0.0422 nan 0.0100 0.0006
## 3 0.0415 nan 0.0100 0.0006
## 4 0.0411 nan 0.0100 0.0001
## 5 0.0406 nan 0.0100 0.0003
## 6 0.0401 nan 0.0100 0.0003
## 7 0.0396 nan 0.0100 0.0002
## 8 0.0394 nan 0.0100 -0.0000
## 9 0.0388 nan 0.0100 0.0005
## 10 0.0383 nan 0.0100 0.0005
## 20 0.0344 nan 0.0100 0.0004
## 40 0.0274 nan 0.0100 0.0001
## 60 0.0227 nan 0.0100 -0.0000
## 80 0.0184 nan 0.0100 0.0002
## 100 0.0152 nan 0.0100 0.0001
## 120 0.0123 nan 0.0100 0.0001
## 140 0.0101 nan 0.0100 -0.0000
## 160 0.0085 nan 0.0100 0.0000
## 180 0.0073 nan 0.0100 -0.0000
## 200 0.0062 nan 0.0100 0.0001
##
## - Fold18: shrinkage=0.01, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold18: shrinkage=0.01, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0429 nan 0.0100 0.0004
## 2 0.0423 nan 0.0100 0.0004
## 3 0.0419 nan 0.0100 0.0004
## 4 0.0415 nan 0.0100 0.0003
## 5 0.0411 nan 0.0100 0.0005
## 6 0.0404 nan 0.0100 0.0005
## 7 0.0398 nan 0.0100 0.0005
## 8 0.0397 nan 0.0100 -0.0002
## 9 0.0394 nan 0.0100 0.0002
## 10 0.0391 nan 0.0100 0.0003
## 20 0.0347 nan 0.0100 0.0001
## 40 0.0279 nan 0.0100 0.0002
## 60 0.0229 nan 0.0100 0.0001
## 80 0.0189 nan 0.0100 0.0001
## 100 0.0162 nan 0.0100 0.0000
## 120 0.0142 nan 0.0100 0.0001
## 140 0.0123 nan 0.0100 0.0001
## 160 0.0109 nan 0.0100 0.0001
## 180 0.0095 nan 0.0100 0.0000
## 200 0.0086 nan 0.0100 0.0000
##
## - Fold18: shrinkage=0.01, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold18: shrinkage=0.01, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0428 nan 0.0100 0.0003
## 2 0.0422 nan 0.0100 0.0006
## 3 0.0418 nan 0.0100 0.0004
## 4 0.0416 nan 0.0100 -0.0001
## 5 0.0409 nan 0.0100 0.0004
## 6 0.0402 nan 0.0100 0.0006
## 7 0.0395 nan 0.0100 0.0004
## 8 0.0390 nan 0.0100 0.0004
## 9 0.0386 nan 0.0100 0.0001
## 10 0.0381 nan 0.0100 0.0004
## 20 0.0325 nan 0.0100 0.0002
## 40 0.0252 nan 0.0100 0.0003
## 60 0.0194 nan 0.0100 0.0001
## 80 0.0151 nan 0.0100 0.0000
## 100 0.0118 nan 0.0100 0.0001
## 120 0.0093 nan 0.0100 0.0001
## 140 0.0074 nan 0.0100 0.0001
## 160 0.0059 nan 0.0100 0.0000
## 180 0.0047 nan 0.0100 0.0000
## 200 0.0038 nan 0.0100 0.0000
##
## - Fold18: shrinkage=0.01, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold18: shrinkage=0.01, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0429 nan 0.0100 0.0004
## 2 0.0423 nan 0.0100 0.0004
## 3 0.0415 nan 0.0100 0.0006
## 4 0.0410 nan 0.0100 0.0004
## 5 0.0405 nan 0.0100 0.0002
## 6 0.0401 nan 0.0100 0.0005
## 7 0.0396 nan 0.0100 0.0005
## 8 0.0390 nan 0.0100 0.0006
## 9 0.0385 nan 0.0100 0.0005
## 10 0.0379 nan 0.0100 0.0006
## 20 0.0331 nan 0.0100 0.0004
## 40 0.0260 nan 0.0100 0.0002
## 60 0.0203 nan 0.0100 0.0002
## 80 0.0157 nan 0.0100 0.0002
## 100 0.0124 nan 0.0100 0.0001
## 120 0.0102 nan 0.0100 0.0001
## 140 0.0084 nan 0.0100 -0.0000
## 160 0.0068 nan 0.0100 0.0001
## 180 0.0057 nan 0.0100 -0.0000
## 200 0.0047 nan 0.0100 0.0000
##
## - Fold18: shrinkage=0.01, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold18: shrinkage=0.01, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0429 nan 0.0100 0.0004
## 2 0.0424 nan 0.0100 0.0002
## 3 0.0418 nan 0.0100 0.0005
## 4 0.0413 nan 0.0100 0.0002
## 5 0.0408 nan 0.0100 0.0005
## 6 0.0403 nan 0.0100 0.0005
## 7 0.0400 nan 0.0100 0.0002
## 8 0.0395 nan 0.0100 0.0004
## 9 0.0389 nan 0.0100 0.0003
## 10 0.0384 nan 0.0100 0.0005
## 20 0.0343 nan 0.0100 0.0002
## 40 0.0273 nan 0.0100 0.0002
## 60 0.0225 nan 0.0100 0.0002
## 80 0.0187 nan 0.0100 0.0002
## 100 0.0159 nan 0.0100 0.0001
## 120 0.0134 nan 0.0100 0.0000
## 140 0.0116 nan 0.0100 0.0000
## 160 0.0103 nan 0.0100 -0.0000
## 180 0.0092 nan 0.0100 0.0000
## 200 0.0084 nan 0.0100 -0.0000
##
## - Fold18: shrinkage=0.01, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold18: shrinkage=0.01, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0430 nan 0.0100 -0.0000
## 2 0.0425 nan 0.0100 0.0003
## 3 0.0418 nan 0.0100 0.0003
## 4 0.0411 nan 0.0100 0.0005
## 5 0.0407 nan 0.0100 0.0004
## 6 0.0403 nan 0.0100 0.0002
## 7 0.0396 nan 0.0100 0.0006
## 8 0.0389 nan 0.0100 0.0007
## 9 0.0382 nan 0.0100 0.0005
## 10 0.0375 nan 0.0100 0.0004
## 20 0.0322 nan 0.0100 0.0005
## 40 0.0232 nan 0.0100 0.0003
## 60 0.0174 nan 0.0100 0.0002
## 80 0.0137 nan 0.0100 0.0001
## 100 0.0104 nan 0.0100 0.0002
## 120 0.0081 nan 0.0100 0.0001
## 140 0.0062 nan 0.0100 0.0001
## 160 0.0049 nan 0.0100 0.0000
## 180 0.0038 nan 0.0100 0.0000
## 200 0.0031 nan 0.0100 0.0000
##
## - Fold18: shrinkage=0.01, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold18: shrinkage=0.01, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0426 nan 0.0100 0.0002
## 2 0.0422 nan 0.0100 0.0003
## 3 0.0417 nan 0.0100 0.0005
## 4 0.0410 nan 0.0100 0.0003
## 5 0.0407 nan 0.0100 0.0001
## 6 0.0404 nan 0.0100 0.0001
## 7 0.0400 nan 0.0100 0.0004
## 8 0.0395 nan 0.0100 0.0000
## 9 0.0391 nan 0.0100 0.0005
## 10 0.0384 nan 0.0100 0.0004
## 20 0.0339 nan 0.0100 0.0005
## 40 0.0255 nan 0.0100 0.0001
## 60 0.0196 nan 0.0100 0.0002
## 80 0.0154 nan 0.0100 -0.0001
## 100 0.0124 nan 0.0100 -0.0000
## 120 0.0099 nan 0.0100 0.0001
## 140 0.0079 nan 0.0100 0.0001
## 160 0.0063 nan 0.0100 -0.0000
## 180 0.0054 nan 0.0100 0.0000
## 200 0.0046 nan 0.0100 -0.0000
##
## - Fold18: shrinkage=0.01, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold18: shrinkage=0.01, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0428 nan 0.0100 0.0003
## 2 0.0422 nan 0.0100 0.0004
## 3 0.0416 nan 0.0100 0.0005
## 4 0.0411 nan 0.0100 0.0004
## 5 0.0403 nan 0.0100 0.0005
## 6 0.0398 nan 0.0100 0.0003
## 7 0.0394 nan 0.0100 0.0002
## 8 0.0390 nan 0.0100 0.0005
## 9 0.0385 nan 0.0100 0.0001
## 10 0.0381 nan 0.0100 0.0005
## 20 0.0342 nan 0.0100 0.0004
## 40 0.0274 nan 0.0100 0.0001
## 60 0.0228 nan 0.0100 0.0001
## 80 0.0185 nan 0.0100 0.0002
## 100 0.0156 nan 0.0100 -0.0000
## 120 0.0133 nan 0.0100 0.0000
## 140 0.0116 nan 0.0100 -0.0000
## 160 0.0102 nan 0.0100 0.0001
## 180 0.0092 nan 0.0100 -0.0000
## 200 0.0081 nan 0.0100 0.0000
##
## - Fold18: shrinkage=0.01, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold18: shrinkage=0.05, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0419 nan 0.0500 0.0006
## 2 0.0397 nan 0.0500 0.0009
## 3 0.0368 nan 0.0500 0.0029
## 4 0.0342 nan 0.0500 0.0024
## 5 0.0319 nan 0.0500 0.0020
## 6 0.0303 nan 0.0500 0.0014
## 7 0.0285 nan 0.0500 0.0017
## 8 0.0267 nan 0.0500 0.0011
## 9 0.0254 nan 0.0500 0.0011
## 10 0.0237 nan 0.0500 0.0020
## 20 0.0152 nan 0.0500 0.0000
## 40 0.0062 nan 0.0500 0.0001
## 60 0.0027 nan 0.0500 -0.0000
## 80 0.0014 nan 0.0500 -0.0000
## 100 0.0009 nan 0.0500 -0.0000
## 120 0.0005 nan 0.0500 -0.0000
## 140 0.0003 nan 0.0500 0.0000
## 160 0.0002 nan 0.0500 -0.0000
## 180 0.0001 nan 0.0500 0.0000
## 200 0.0001 nan 0.0500 -0.0000
##
## - Fold18: shrinkage=0.05, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold18: shrinkage=0.05, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0417 nan 0.0500 0.0006
## 2 0.0398 nan 0.0500 0.0020
## 3 0.0381 nan 0.0500 0.0006
## 4 0.0361 nan 0.0500 0.0002
## 5 0.0339 nan 0.0500 0.0020
## 6 0.0310 nan 0.0500 0.0021
## 7 0.0303 nan 0.0500 0.0001
## 8 0.0288 nan 0.0500 0.0011
## 9 0.0272 nan 0.0500 0.0006
## 10 0.0254 nan 0.0500 0.0004
## 20 0.0153 nan 0.0500 0.0003
## 40 0.0066 nan 0.0500 0.0001
## 60 0.0034 nan 0.0500 -0.0000
## 80 0.0021 nan 0.0500 0.0000
## 100 0.0012 nan 0.0500 0.0000
## 120 0.0007 nan 0.0500 -0.0000
## 140 0.0005 nan 0.0500 -0.0000
## 160 0.0003 nan 0.0500 0.0000
## 180 0.0002 nan 0.0500 0.0000
## 200 0.0001 nan 0.0500 -0.0000
##
## - Fold18: shrinkage=0.05, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold18: shrinkage=0.05, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0417 nan 0.0500 0.0017
## 2 0.0394 nan 0.0500 0.0014
## 3 0.0369 nan 0.0500 0.0019
## 4 0.0345 nan 0.0500 0.0011
## 5 0.0327 nan 0.0500 0.0015
## 6 0.0305 nan 0.0500 0.0021
## 7 0.0291 nan 0.0500 0.0015
## 8 0.0272 nan 0.0500 0.0016
## 9 0.0255 nan 0.0500 0.0013
## 10 0.0245 nan 0.0500 0.0011
## 20 0.0160 nan 0.0500 0.0004
## 40 0.0081 nan 0.0500 0.0001
## 60 0.0051 nan 0.0500 0.0001
## 80 0.0037 nan 0.0500 0.0001
## 100 0.0024 nan 0.0500 -0.0000
## 120 0.0014 nan 0.0500 -0.0000
## 140 0.0011 nan 0.0500 -0.0000
## 160 0.0009 nan 0.0500 0.0000
## 180 0.0006 nan 0.0500 0.0000
## 200 0.0005 nan 0.0500 -0.0000
##
## - Fold18: shrinkage=0.05, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold18: shrinkage=0.05, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0409 nan 0.0500 -0.0000
## 2 0.0385 nan 0.0500 0.0024
## 3 0.0372 nan 0.0500 -0.0000
## 4 0.0339 nan 0.0500 0.0032
## 5 0.0323 nan 0.0500 0.0013
## 6 0.0309 nan 0.0500 0.0006
## 7 0.0290 nan 0.0500 0.0015
## 8 0.0273 nan 0.0500 0.0015
## 9 0.0262 nan 0.0500 0.0000
## 10 0.0243 nan 0.0500 0.0020
## 20 0.0130 nan 0.0500 0.0003
## 40 0.0040 nan 0.0500 0.0002
## 60 0.0015 nan 0.0500 0.0000
## 80 0.0006 nan 0.0500 0.0000
## 100 0.0003 nan 0.0500 0.0000
## 120 0.0002 nan 0.0500 -0.0000
## 140 0.0001 nan 0.0500 -0.0000
## 160 0.0000 nan 0.0500 -0.0000
## 180 0.0000 nan 0.0500 0.0000
## 200 0.0000 nan 0.0500 -0.0000
##
## - Fold18: shrinkage=0.05, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold18: shrinkage=0.05, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0397 nan 0.0500 0.0036
## 2 0.0375 nan 0.0500 0.0007
## 3 0.0350 nan 0.0500 0.0029
## 4 0.0328 nan 0.0500 0.0018
## 5 0.0310 nan 0.0500 0.0019
## 6 0.0287 nan 0.0500 0.0017
## 7 0.0270 nan 0.0500 0.0012
## 8 0.0255 nan 0.0500 0.0018
## 9 0.0251 nan 0.0500 0.0000
## 10 0.0238 nan 0.0500 0.0001
## 20 0.0135 nan 0.0500 0.0009
## 40 0.0056 nan 0.0500 0.0001
## 60 0.0026 nan 0.0500 0.0000
## 80 0.0012 nan 0.0500 -0.0000
## 100 0.0007 nan 0.0500 -0.0000
## 120 0.0004 nan 0.0500 -0.0000
## 140 0.0002 nan 0.0500 0.0000
## 160 0.0001 nan 0.0500 -0.0000
## 180 0.0001 nan 0.0500 0.0000
## 200 0.0000 nan 0.0500 0.0000
##
## - Fold18: shrinkage=0.05, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold18: shrinkage=0.05, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0409 nan 0.0500 0.0025
## 2 0.0381 nan 0.0500 0.0025
## 3 0.0366 nan 0.0500 0.0010
## 4 0.0349 nan 0.0500 0.0015
## 5 0.0335 nan 0.0500 0.0008
## 6 0.0317 nan 0.0500 0.0016
## 7 0.0305 nan 0.0500 0.0001
## 8 0.0298 nan 0.0500 -0.0001
## 9 0.0287 nan 0.0500 0.0009
## 10 0.0274 nan 0.0500 0.0012
## 20 0.0171 nan 0.0500 0.0008
## 40 0.0091 nan 0.0500 0.0000
## 60 0.0054 nan 0.0500 0.0001
## 80 0.0036 nan 0.0500 0.0001
## 100 0.0024 nan 0.0500 0.0000
## 120 0.0017 nan 0.0500 -0.0000
## 140 0.0012 nan 0.0500 -0.0000
## 160 0.0009 nan 0.0500 -0.0000
## 180 0.0007 nan 0.0500 -0.0000
## 200 0.0005 nan 0.0500 -0.0000
##
## - Fold18: shrinkage=0.05, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold18: shrinkage=0.05, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0401 nan 0.0500 0.0018
## 2 0.0373 nan 0.0500 0.0014
## 3 0.0338 nan 0.0500 0.0019
## 4 0.0310 nan 0.0500 0.0021
## 5 0.0293 nan 0.0500 0.0020
## 6 0.0279 nan 0.0500 0.0014
## 7 0.0263 nan 0.0500 0.0004
## 8 0.0242 nan 0.0500 0.0015
## 9 0.0228 nan 0.0500 0.0014
## 10 0.0213 nan 0.0500 0.0009
## 20 0.0115 nan 0.0500 0.0002
## 40 0.0032 nan 0.0500 0.0000
## 60 0.0013 nan 0.0500 -0.0000
## 80 0.0005 nan 0.0500 0.0000
## 100 0.0002 nan 0.0500 -0.0000
## 120 0.0001 nan 0.0500 -0.0000
## 140 0.0000 nan 0.0500 -0.0000
## 160 0.0000 nan 0.0500 -0.0000
## 180 0.0000 nan 0.0500 -0.0000
## 200 0.0000 nan 0.0500 -0.0000
##
## - Fold18: shrinkage=0.05, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold18: shrinkage=0.05, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0402 nan 0.0500 0.0028
## 2 0.0371 nan 0.0500 0.0026
## 3 0.0356 nan 0.0500 0.0005
## 4 0.0328 nan 0.0500 0.0025
## 5 0.0302 nan 0.0500 0.0019
## 6 0.0279 nan 0.0500 0.0020
## 7 0.0258 nan 0.0500 0.0011
## 8 0.0244 nan 0.0500 0.0005
## 9 0.0237 nan 0.0500 -0.0002
## 10 0.0220 nan 0.0500 0.0009
## 20 0.0111 nan 0.0500 0.0000
## 40 0.0041 nan 0.0500 0.0002
## 60 0.0016 nan 0.0500 0.0000
## 80 0.0008 nan 0.0500 -0.0000
## 100 0.0005 nan 0.0500 -0.0000
## 120 0.0003 nan 0.0500 -0.0000
## 140 0.0002 nan 0.0500 -0.0000
## 160 0.0001 nan 0.0500 0.0000
## 180 0.0001 nan 0.0500 -0.0000
## 200 0.0001 nan 0.0500 -0.0000
##
## - Fold18: shrinkage=0.05, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold18: shrinkage=0.05, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0406 nan 0.0500 0.0029
## 2 0.0378 nan 0.0500 0.0020
## 3 0.0356 nan 0.0500 0.0025
## 4 0.0337 nan 0.0500 0.0014
## 5 0.0316 nan 0.0500 0.0018
## 6 0.0299 nan 0.0500 0.0007
## 7 0.0279 nan 0.0500 0.0016
## 8 0.0263 nan 0.0500 0.0008
## 9 0.0249 nan 0.0500 0.0013
## 10 0.0232 nan 0.0500 0.0005
## 20 0.0160 nan 0.0500 -0.0003
## 40 0.0076 nan 0.0500 0.0001
## 60 0.0046 nan 0.0500 0.0001
## 80 0.0031 nan 0.0500 0.0001
## 100 0.0021 nan 0.0500 0.0000
## 120 0.0017 nan 0.0500 -0.0000
## 140 0.0012 nan 0.0500 -0.0000
## 160 0.0009 nan 0.0500 -0.0000
## 180 0.0006 nan 0.0500 0.0000
## 200 0.0004 nan 0.0500 0.0000
##
## - Fold18: shrinkage=0.05, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold18: shrinkage=0.10, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0380 nan 0.1000 0.0046
## 2 0.0336 nan 0.1000 0.0043
## 3 0.0300 nan 0.1000 0.0020
## 4 0.0260 nan 0.1000 0.0026
## 5 0.0238 nan 0.1000 0.0003
## 6 0.0218 nan 0.1000 0.0017
## 7 0.0198 nan 0.1000 0.0004
## 8 0.0177 nan 0.1000 0.0014
## 9 0.0160 nan 0.1000 0.0007
## 10 0.0149 nan 0.1000 -0.0007
## 20 0.0056 nan 0.1000 0.0003
## 40 0.0015 nan 0.1000 0.0001
## 60 0.0005 nan 0.1000 0.0000
## 80 0.0002 nan 0.1000 -0.0000
## 100 0.0001 nan 0.1000 -0.0000
## 120 0.0001 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold18: shrinkage=0.10, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold18: shrinkage=0.10, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0391 nan 0.1000 0.0049
## 2 0.0368 nan 0.1000 -0.0008
## 3 0.0323 nan 0.1000 0.0009
## 4 0.0286 nan 0.1000 0.0038
## 5 0.0254 nan 0.1000 0.0028
## 6 0.0224 nan 0.1000 0.0032
## 7 0.0200 nan 0.1000 0.0021
## 8 0.0182 nan 0.1000 0.0010
## 9 0.0167 nan 0.1000 0.0009
## 10 0.0151 nan 0.1000 0.0014
## 20 0.0064 nan 0.1000 0.0003
## 40 0.0023 nan 0.1000 0.0001
## 60 0.0009 nan 0.1000 0.0000
## 80 0.0005 nan 0.1000 -0.0000
## 100 0.0002 nan 0.1000 -0.0000
## 120 0.0001 nan 0.1000 0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold18: shrinkage=0.10, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold18: shrinkage=0.10, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0393 nan 0.1000 0.0011
## 2 0.0334 nan 0.1000 0.0036
## 3 0.0291 nan 0.1000 0.0043
## 4 0.0260 nan 0.1000 0.0029
## 5 0.0234 nan 0.1000 0.0008
## 6 0.0208 nan 0.1000 0.0025
## 7 0.0193 nan 0.1000 0.0007
## 8 0.0177 nan 0.1000 0.0014
## 9 0.0150 nan 0.1000 0.0008
## 10 0.0136 nan 0.1000 0.0014
## 20 0.0085 nan 0.1000 0.0006
## 40 0.0034 nan 0.1000 -0.0001
## 60 0.0011 nan 0.1000 -0.0001
## 80 0.0005 nan 0.1000 -0.0000
## 100 0.0003 nan 0.1000 0.0000
## 120 0.0002 nan 0.1000 -0.0000
## 140 0.0001 nan 0.1000 -0.0000
## 160 0.0001 nan 0.1000 0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold18: shrinkage=0.10, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold18: shrinkage=0.10, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0377 nan 0.1000 0.0048
## 2 0.0331 nan 0.1000 0.0049
## 3 0.0293 nan 0.1000 0.0017
## 4 0.0241 nan 0.1000 0.0048
## 5 0.0211 nan 0.1000 0.0029
## 6 0.0195 nan 0.1000 0.0015
## 7 0.0173 nan 0.1000 0.0006
## 8 0.0156 nan 0.1000 -0.0003
## 9 0.0136 nan 0.1000 0.0015
## 10 0.0120 nan 0.1000 0.0015
## 20 0.0050 nan 0.1000 0.0001
## 40 0.0013 nan 0.1000 0.0000
## 60 0.0003 nan 0.1000 0.0000
## 80 0.0001 nan 0.1000 0.0000
## 100 0.0000 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 0.0000
##
## - Fold18: shrinkage=0.10, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold18: shrinkage=0.10, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0387 nan 0.1000 0.0038
## 2 0.0321 nan 0.1000 0.0036
## 3 0.0268 nan 0.1000 0.0040
## 4 0.0246 nan 0.1000 0.0025
## 5 0.0225 nan 0.1000 0.0021
## 6 0.0196 nan 0.1000 0.0004
## 7 0.0174 nan 0.1000 0.0017
## 8 0.0157 nan 0.1000 0.0017
## 9 0.0132 nan 0.1000 0.0022
## 10 0.0122 nan 0.1000 0.0010
## 20 0.0041 nan 0.1000 0.0001
## 40 0.0011 nan 0.1000 -0.0000
## 60 0.0004 nan 0.1000 -0.0000
## 80 0.0002 nan 0.1000 -0.0000
## 100 0.0001 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold18: shrinkage=0.10, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold18: shrinkage=0.10, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0376 nan 0.1000 0.0049
## 2 0.0345 nan 0.1000 0.0003
## 3 0.0315 nan 0.1000 0.0013
## 4 0.0291 nan 0.1000 0.0002
## 5 0.0265 nan 0.1000 0.0021
## 6 0.0241 nan 0.1000 0.0016
## 7 0.0214 nan 0.1000 0.0025
## 8 0.0189 nan 0.1000 0.0018
## 9 0.0174 nan 0.1000 0.0014
## 10 0.0160 nan 0.1000 0.0014
## 20 0.0094 nan 0.1000 0.0003
## 40 0.0038 nan 0.1000 -0.0001
## 60 0.0016 nan 0.1000 -0.0001
## 80 0.0007 nan 0.1000 -0.0000
## 100 0.0003 nan 0.1000 -0.0000
## 120 0.0002 nan 0.1000 -0.0000
## 140 0.0001 nan 0.1000 -0.0000
## 160 0.0001 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold18: shrinkage=0.10, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold18: shrinkage=0.10, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0395 nan 0.1000 0.0027
## 2 0.0338 nan 0.1000 0.0040
## 3 0.0275 nan 0.1000 0.0059
## 4 0.0238 nan 0.1000 0.0021
## 5 0.0210 nan 0.1000 0.0019
## 6 0.0200 nan 0.1000 -0.0010
## 7 0.0172 nan 0.1000 0.0027
## 8 0.0146 nan 0.1000 0.0013
## 9 0.0123 nan 0.1000 0.0016
## 10 0.0104 nan 0.1000 0.0019
## 20 0.0036 nan 0.1000 -0.0001
## 40 0.0005 nan 0.1000 -0.0000
## 60 0.0001 nan 0.1000 -0.0000
## 80 0.0000 nan 0.1000 0.0000
## 100 0.0000 nan 0.1000 0.0000
## 120 0.0000 nan 0.1000 0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 0.0000
##
## - Fold18: shrinkage=0.10, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold18: shrinkage=0.10, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0375 nan 0.1000 0.0054
## 2 0.0312 nan 0.1000 0.0028
## 3 0.0249 nan 0.1000 0.0044
## 4 0.0206 nan 0.1000 0.0031
## 5 0.0184 nan 0.1000 0.0023
## 6 0.0170 nan 0.1000 0.0008
## 7 0.0163 nan 0.1000 -0.0012
## 8 0.0141 nan 0.1000 0.0007
## 9 0.0119 nan 0.1000 0.0015
## 10 0.0111 nan 0.1000 0.0001
## 20 0.0042 nan 0.1000 -0.0000
## 40 0.0008 nan 0.1000 0.0000
## 60 0.0002 nan 0.1000 -0.0000
## 80 0.0001 nan 0.1000 -0.0000
## 100 0.0000 nan 0.1000 0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold18: shrinkage=0.10, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold18: shrinkage=0.10, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0377 nan 0.1000 0.0044
## 2 0.0326 nan 0.1000 0.0036
## 3 0.0294 nan 0.1000 0.0027
## 4 0.0258 nan 0.1000 0.0028
## 5 0.0252 nan 0.1000 -0.0001
## 6 0.0224 nan 0.1000 0.0014
## 7 0.0203 nan 0.1000 0.0021
## 8 0.0186 nan 0.1000 0.0014
## 9 0.0173 nan 0.1000 0.0016
## 10 0.0155 nan 0.1000 -0.0000
## 20 0.0079 nan 0.1000 0.0004
## 40 0.0028 nan 0.1000 0.0001
## 60 0.0013 nan 0.1000 -0.0000
## 80 0.0008 nan 0.1000 -0.0000
## 100 0.0005 nan 0.1000 -0.0000
## 120 0.0003 nan 0.1000 0.0000
## 140 0.0002 nan 0.1000 -0.0000
## 160 0.0001 nan 0.1000 -0.0000
## 180 0.0001 nan 0.1000 0.0000
## 200 0.0001 nan 0.1000 -0.0000
##
## - Fold18: shrinkage=0.10, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold19: shrinkage=0.01, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0425 nan 0.0100 0.0004
## 2 0.0421 nan 0.0100 -0.0000
## 3 0.0414 nan 0.0100 0.0005
## 4 0.0408 nan 0.0100 0.0006
## 5 0.0405 nan 0.0100 0.0004
## 6 0.0400 nan 0.0100 0.0006
## 7 0.0393 nan 0.0100 0.0005
## 8 0.0388 nan 0.0100 0.0005
## 9 0.0383 nan 0.0100 0.0005
## 10 0.0379 nan 0.0100 0.0001
## 20 0.0338 nan 0.0100 0.0001
## 40 0.0271 nan 0.0100 0.0000
## 60 0.0221 nan 0.0100 0.0003
## 80 0.0178 nan 0.0100 0.0002
## 100 0.0149 nan 0.0100 -0.0000
## 120 0.0124 nan 0.0100 -0.0000
## 140 0.0105 nan 0.0100 0.0000
## 160 0.0087 nan 0.0100 0.0000
## 180 0.0074 nan 0.0100 0.0001
## 200 0.0061 nan 0.0100 0.0000
##
## - Fold19: shrinkage=0.01, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold19: shrinkage=0.01, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0423 nan 0.0100 0.0006
## 2 0.0416 nan 0.0100 0.0004
## 3 0.0409 nan 0.0100 0.0006
## 4 0.0403 nan 0.0100 0.0004
## 5 0.0398 nan 0.0100 0.0005
## 6 0.0394 nan 0.0100 0.0005
## 7 0.0388 nan 0.0100 0.0004
## 8 0.0386 nan 0.0100 -0.0000
## 9 0.0380 nan 0.0100 0.0005
## 10 0.0375 nan 0.0100 0.0005
## 20 0.0333 nan 0.0100 0.0002
## 40 0.0269 nan 0.0100 -0.0000
## 60 0.0219 nan 0.0100 0.0002
## 80 0.0176 nan 0.0100 0.0002
## 100 0.0146 nan 0.0100 0.0000
## 120 0.0118 nan 0.0100 0.0001
## 140 0.0099 nan 0.0100 0.0000
## 160 0.0082 nan 0.0100 -0.0000
## 180 0.0071 nan 0.0100 0.0000
## 200 0.0059 nan 0.0100 0.0000
##
## - Fold19: shrinkage=0.01, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold19: shrinkage=0.01, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0425 nan 0.0100 0.0005
## 2 0.0419 nan 0.0100 0.0006
## 3 0.0415 nan 0.0100 0.0004
## 4 0.0409 nan 0.0100 0.0004
## 5 0.0404 nan 0.0100 0.0005
## 6 0.0398 nan 0.0100 0.0005
## 7 0.0392 nan 0.0100 0.0005
## 8 0.0387 nan 0.0100 0.0004
## 9 0.0382 nan 0.0100 0.0005
## 10 0.0378 nan 0.0100 0.0002
## 20 0.0339 nan 0.0100 0.0004
## 40 0.0273 nan 0.0100 -0.0000
## 60 0.0224 nan 0.0100 0.0002
## 80 0.0188 nan 0.0100 0.0001
## 100 0.0158 nan 0.0100 0.0000
## 120 0.0136 nan 0.0100 -0.0000
## 140 0.0117 nan 0.0100 -0.0000
## 160 0.0103 nan 0.0100 0.0000
## 180 0.0091 nan 0.0100 0.0000
## 200 0.0080 nan 0.0100 0.0000
##
## - Fold19: shrinkage=0.01, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold19: shrinkage=0.01, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0426 nan 0.0100 0.0004
## 2 0.0421 nan 0.0100 0.0004
## 3 0.0415 nan 0.0100 0.0003
## 4 0.0408 nan 0.0100 0.0003
## 5 0.0403 nan 0.0100 0.0001
## 6 0.0397 nan 0.0100 0.0002
## 7 0.0393 nan 0.0100 0.0005
## 8 0.0386 nan 0.0100 0.0007
## 9 0.0382 nan 0.0100 0.0003
## 10 0.0377 nan 0.0100 0.0004
## 20 0.0332 nan 0.0100 0.0005
## 40 0.0252 nan 0.0100 0.0002
## 60 0.0187 nan 0.0100 0.0002
## 80 0.0146 nan 0.0100 0.0001
## 100 0.0112 nan 0.0100 0.0002
## 120 0.0088 nan 0.0100 0.0000
## 140 0.0070 nan 0.0100 -0.0000
## 160 0.0057 nan 0.0100 0.0000
## 180 0.0046 nan 0.0100 0.0000
## 200 0.0038 nan 0.0100 0.0000
##
## - Fold19: shrinkage=0.01, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold19: shrinkage=0.01, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0424 nan 0.0100 0.0005
## 2 0.0420 nan 0.0100 0.0001
## 3 0.0414 nan 0.0100 0.0006
## 4 0.0408 nan 0.0100 0.0004
## 5 0.0402 nan 0.0100 0.0004
## 6 0.0397 nan 0.0100 0.0004
## 7 0.0391 nan 0.0100 0.0006
## 8 0.0387 nan 0.0100 0.0003
## 9 0.0382 nan 0.0100 0.0005
## 10 0.0375 nan 0.0100 0.0006
## 20 0.0321 nan 0.0100 0.0003
## 40 0.0248 nan 0.0100 0.0001
## 60 0.0198 nan 0.0100 0.0001
## 80 0.0155 nan 0.0100 0.0002
## 100 0.0122 nan 0.0100 0.0001
## 120 0.0102 nan 0.0100 0.0000
## 140 0.0083 nan 0.0100 0.0000
## 160 0.0068 nan 0.0100 0.0000
## 180 0.0055 nan 0.0100 0.0000
## 200 0.0047 nan 0.0100 -0.0000
##
## - Fold19: shrinkage=0.01, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold19: shrinkage=0.01, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0425 nan 0.0100 0.0004
## 2 0.0420 nan 0.0100 0.0005
## 3 0.0416 nan 0.0100 0.0003
## 4 0.0412 nan 0.0100 0.0005
## 5 0.0405 nan 0.0100 0.0006
## 6 0.0400 nan 0.0100 0.0003
## 7 0.0395 nan 0.0100 0.0006
## 8 0.0389 nan 0.0100 0.0004
## 9 0.0384 nan 0.0100 0.0005
## 10 0.0380 nan 0.0100 0.0004
## 20 0.0340 nan 0.0100 0.0003
## 40 0.0274 nan 0.0100 0.0003
## 60 0.0226 nan 0.0100 0.0000
## 80 0.0189 nan 0.0100 0.0001
## 100 0.0160 nan 0.0100 0.0001
## 120 0.0136 nan 0.0100 0.0000
## 140 0.0118 nan 0.0100 0.0001
## 160 0.0103 nan 0.0100 0.0000
## 180 0.0093 nan 0.0100 -0.0000
## 200 0.0082 nan 0.0100 0.0000
##
## - Fold19: shrinkage=0.01, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold19: shrinkage=0.01, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0425 nan 0.0100 0.0005
## 2 0.0419 nan 0.0100 0.0001
## 3 0.0413 nan 0.0100 0.0006
## 4 0.0408 nan 0.0100 0.0004
## 5 0.0404 nan 0.0100 0.0001
## 6 0.0396 nan 0.0100 0.0008
## 7 0.0389 nan 0.0100 0.0006
## 8 0.0385 nan 0.0100 -0.0000
## 9 0.0380 nan 0.0100 0.0003
## 10 0.0375 nan 0.0100 0.0006
## 20 0.0325 nan 0.0100 0.0003
## 40 0.0240 nan 0.0100 0.0003
## 60 0.0186 nan 0.0100 0.0002
## 80 0.0141 nan 0.0100 0.0001
## 100 0.0108 nan 0.0100 0.0001
## 120 0.0082 nan 0.0100 0.0001
## 140 0.0062 nan 0.0100 0.0000
## 160 0.0048 nan 0.0100 0.0000
## 180 0.0038 nan 0.0100 0.0001
## 200 0.0031 nan 0.0100 -0.0000
##
## - Fold19: shrinkage=0.01, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold19: shrinkage=0.01, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0425 nan 0.0100 0.0002
## 2 0.0418 nan 0.0100 0.0006
## 3 0.0410 nan 0.0100 0.0005
## 4 0.0404 nan 0.0100 0.0007
## 5 0.0398 nan 0.0100 0.0004
## 6 0.0391 nan 0.0100 0.0004
## 7 0.0387 nan 0.0100 0.0003
## 8 0.0382 nan 0.0100 0.0001
## 9 0.0379 nan 0.0100 0.0000
## 10 0.0375 nan 0.0100 0.0002
## 20 0.0319 nan 0.0100 0.0004
## 40 0.0246 nan 0.0100 0.0003
## 60 0.0185 nan 0.0100 0.0000
## 80 0.0143 nan 0.0100 0.0000
## 100 0.0114 nan 0.0100 0.0001
## 120 0.0089 nan 0.0100 0.0000
## 140 0.0071 nan 0.0100 0.0000
## 160 0.0058 nan 0.0100 0.0000
## 180 0.0048 nan 0.0100 0.0000
## 200 0.0040 nan 0.0100 0.0000
##
## - Fold19: shrinkage=0.01, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold19: shrinkage=0.01, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0424 nan 0.0100 0.0005
## 2 0.0422 nan 0.0100 0.0001
## 3 0.0419 nan 0.0100 0.0001
## 4 0.0413 nan 0.0100 0.0002
## 5 0.0407 nan 0.0100 0.0002
## 6 0.0402 nan 0.0100 0.0005
## 7 0.0396 nan 0.0100 0.0005
## 8 0.0393 nan 0.0100 0.0002
## 9 0.0388 nan 0.0100 0.0005
## 10 0.0384 nan 0.0100 0.0002
## 20 0.0344 nan 0.0100 0.0004
## 40 0.0280 nan 0.0100 0.0001
## 60 0.0234 nan 0.0100 0.0001
## 80 0.0193 nan 0.0100 0.0002
## 100 0.0163 nan 0.0100 0.0001
## 120 0.0140 nan 0.0100 0.0001
## 140 0.0122 nan 0.0100 0.0001
## 160 0.0104 nan 0.0100 0.0000
## 180 0.0094 nan 0.0100 0.0000
## 200 0.0085 nan 0.0100 -0.0000
##
## - Fold19: shrinkage=0.01, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold19: shrinkage=0.05, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0403 nan 0.0500 0.0029
## 2 0.0376 nan 0.0500 0.0018
## 3 0.0347 nan 0.0500 0.0023
## 4 0.0333 nan 0.0500 0.0009
## 5 0.0314 nan 0.0500 0.0013
## 6 0.0302 nan 0.0500 0.0009
## 7 0.0297 nan 0.0500 -0.0003
## 8 0.0279 nan 0.0500 0.0007
## 9 0.0269 nan 0.0500 0.0009
## 10 0.0253 nan 0.0500 0.0014
## 20 0.0161 nan 0.0500 0.0007
## 40 0.0077 nan 0.0500 -0.0000
## 60 0.0040 nan 0.0500 0.0002
## 80 0.0021 nan 0.0500 -0.0000
## 100 0.0012 nan 0.0500 0.0000
## 120 0.0007 nan 0.0500 -0.0000
## 140 0.0004 nan 0.0500 -0.0000
## 160 0.0003 nan 0.0500 0.0000
## 180 0.0002 nan 0.0500 -0.0000
## 200 0.0001 nan 0.0500 -0.0000
##
## - Fold19: shrinkage=0.05, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold19: shrinkage=0.05, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0395 nan 0.0500 0.0027
## 2 0.0369 nan 0.0500 0.0017
## 3 0.0350 nan 0.0500 0.0006
## 4 0.0337 nan 0.0500 -0.0003
## 5 0.0317 nan 0.0500 0.0012
## 6 0.0303 nan 0.0500 0.0016
## 7 0.0290 nan 0.0500 0.0013
## 8 0.0276 nan 0.0500 0.0002
## 9 0.0260 nan 0.0500 0.0016
## 10 0.0253 nan 0.0500 0.0005
## 20 0.0160 nan 0.0500 0.0008
## 40 0.0069 nan 0.0500 0.0003
## 60 0.0037 nan 0.0500 -0.0001
## 80 0.0021 nan 0.0500 -0.0000
## 100 0.0013 nan 0.0500 -0.0000
## 120 0.0008 nan 0.0500 -0.0000
## 140 0.0005 nan 0.0500 -0.0000
## 160 0.0003 nan 0.0500 -0.0000
## 180 0.0002 nan 0.0500 -0.0000
## 200 0.0001 nan 0.0500 -0.0000
##
## - Fold19: shrinkage=0.05, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold19: shrinkage=0.05, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0408 nan 0.0500 0.0012
## 2 0.0396 nan 0.0500 -0.0003
## 3 0.0369 nan 0.0500 0.0023
## 4 0.0363 nan 0.0500 -0.0006
## 5 0.0337 nan 0.0500 0.0019
## 6 0.0313 nan 0.0500 0.0020
## 7 0.0296 nan 0.0500 0.0012
## 8 0.0283 nan 0.0500 0.0015
## 9 0.0271 nan 0.0500 0.0005
## 10 0.0260 nan 0.0500 0.0012
## 20 0.0163 nan 0.0500 0.0003
## 40 0.0090 nan 0.0500 0.0000
## 60 0.0048 nan 0.0500 -0.0000
## 80 0.0033 nan 0.0500 -0.0001
## 100 0.0021 nan 0.0500 0.0000
## 120 0.0014 nan 0.0500 0.0000
## 140 0.0010 nan 0.0500 -0.0000
## 160 0.0008 nan 0.0500 -0.0000
## 180 0.0005 nan 0.0500 0.0000
## 200 0.0004 nan 0.0500 -0.0000
##
## - Fold19: shrinkage=0.05, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold19: shrinkage=0.05, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0400 nan 0.0500 0.0026
## 2 0.0380 nan 0.0500 0.0016
## 3 0.0359 nan 0.0500 0.0026
## 4 0.0342 nan 0.0500 0.0014
## 5 0.0310 nan 0.0500 0.0026
## 6 0.0287 nan 0.0500 0.0016
## 7 0.0267 nan 0.0500 0.0011
## 8 0.0252 nan 0.0500 0.0011
## 9 0.0231 nan 0.0500 0.0011
## 10 0.0211 nan 0.0500 0.0016
## 20 0.0120 nan 0.0500 0.0003
## 40 0.0035 nan 0.0500 0.0001
## 60 0.0013 nan 0.0500 -0.0000
## 80 0.0006 nan 0.0500 -0.0000
## 100 0.0003 nan 0.0500 -0.0000
## 120 0.0001 nan 0.0500 0.0000
## 140 0.0001 nan 0.0500 0.0000
## 160 0.0000 nan 0.0500 0.0000
## 180 0.0000 nan 0.0500 -0.0000
## 200 0.0000 nan 0.0500 -0.0000
##
## - Fold19: shrinkage=0.05, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold19: shrinkage=0.05, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0397 nan 0.0500 0.0035
## 2 0.0375 nan 0.0500 0.0020
## 3 0.0350 nan 0.0500 0.0026
## 4 0.0324 nan 0.0500 0.0021
## 5 0.0312 nan 0.0500 -0.0003
## 6 0.0294 nan 0.0500 0.0020
## 7 0.0267 nan 0.0500 0.0011
## 8 0.0252 nan 0.0500 0.0013
## 9 0.0229 nan 0.0500 0.0010
## 10 0.0208 nan 0.0500 0.0013
## 20 0.0111 nan 0.0500 0.0007
## 40 0.0045 nan 0.0500 0.0002
## 60 0.0020 nan 0.0500 -0.0000
## 80 0.0010 nan 0.0500 0.0000
## 100 0.0006 nan 0.0500 0.0000
## 120 0.0004 nan 0.0500 0.0000
## 140 0.0003 nan 0.0500 -0.0000
## 160 0.0002 nan 0.0500 -0.0000
## 180 0.0001 nan 0.0500 0.0000
## 200 0.0001 nan 0.0500 0.0000
##
## - Fold19: shrinkage=0.05, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold19: shrinkage=0.05, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0408 nan 0.0500 0.0014
## 2 0.0383 nan 0.0500 0.0016
## 3 0.0358 nan 0.0500 0.0023
## 4 0.0329 nan 0.0500 0.0015
## 5 0.0307 nan 0.0500 0.0021
## 6 0.0293 nan 0.0500 0.0010
## 7 0.0277 nan 0.0500 0.0017
## 8 0.0266 nan 0.0500 0.0006
## 9 0.0258 nan 0.0500 -0.0002
## 10 0.0247 nan 0.0500 0.0010
## 20 0.0154 nan 0.0500 0.0006
## 40 0.0080 nan 0.0500 0.0000
## 60 0.0048 nan 0.0500 0.0000
## 80 0.0032 nan 0.0500 0.0000
## 100 0.0023 nan 0.0500 -0.0000
## 120 0.0016 nan 0.0500 -0.0000
## 140 0.0012 nan 0.0500 -0.0000
## 160 0.0009 nan 0.0500 -0.0000
## 180 0.0006 nan 0.0500 -0.0000
## 200 0.0005 nan 0.0500 0.0000
##
## - Fold19: shrinkage=0.05, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold19: shrinkage=0.05, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0395 nan 0.0500 0.0027
## 2 0.0370 nan 0.0500 0.0026
## 3 0.0338 nan 0.0500 0.0025
## 4 0.0310 nan 0.0500 0.0017
## 5 0.0289 nan 0.0500 0.0021
## 6 0.0274 nan 0.0500 0.0010
## 7 0.0258 nan 0.0500 0.0008
## 8 0.0239 nan 0.0500 0.0013
## 9 0.0222 nan 0.0500 0.0006
## 10 0.0212 nan 0.0500 0.0001
## 20 0.0110 nan 0.0500 0.0007
## 40 0.0029 nan 0.0500 0.0000
## 60 0.0009 nan 0.0500 0.0000
## 80 0.0003 nan 0.0500 0.0000
## 100 0.0002 nan 0.0500 -0.0000
## 120 0.0001 nan 0.0500 -0.0000
## 140 0.0000 nan 0.0500 -0.0000
## 160 0.0000 nan 0.0500 -0.0000
## 180 0.0000 nan 0.0500 -0.0000
## 200 0.0000 nan 0.0500 0.0000
##
## - Fold19: shrinkage=0.05, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold19: shrinkage=0.05, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0411 nan 0.0500 0.0007
## 2 0.0392 nan 0.0500 0.0010
## 3 0.0365 nan 0.0500 0.0028
## 4 0.0336 nan 0.0500 0.0016
## 5 0.0308 nan 0.0500 0.0018
## 6 0.0287 nan 0.0500 0.0023
## 7 0.0270 nan 0.0500 0.0009
## 8 0.0256 nan 0.0500 0.0011
## 9 0.0244 nan 0.0500 0.0009
## 10 0.0232 nan 0.0500 0.0009
## 20 0.0136 nan 0.0500 0.0004
## 40 0.0047 nan 0.0500 0.0001
## 60 0.0024 nan 0.0500 -0.0001
## 80 0.0013 nan 0.0500 -0.0000
## 100 0.0008 nan 0.0500 -0.0000
## 120 0.0006 nan 0.0500 -0.0000
## 140 0.0004 nan 0.0500 0.0000
## 160 0.0003 nan 0.0500 -0.0000
## 180 0.0002 nan 0.0500 -0.0000
## 200 0.0001 nan 0.0500 -0.0000
##
## - Fold19: shrinkage=0.05, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold19: shrinkage=0.05, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0399 nan 0.0500 0.0030
## 2 0.0373 nan 0.0500 0.0022
## 3 0.0342 nan 0.0500 0.0016
## 4 0.0323 nan 0.0500 0.0008
## 5 0.0307 nan 0.0500 0.0020
## 6 0.0288 nan 0.0500 0.0011
## 7 0.0274 nan 0.0500 0.0014
## 8 0.0267 nan 0.0500 0.0003
## 9 0.0255 nan 0.0500 0.0006
## 10 0.0238 nan 0.0500 0.0014
## 20 0.0135 nan 0.0500 0.0005
## 40 0.0064 nan 0.0500 0.0002
## 60 0.0037 nan 0.0500 0.0000
## 80 0.0025 nan 0.0500 -0.0000
## 100 0.0016 nan 0.0500 -0.0000
## 120 0.0011 nan 0.0500 0.0000
## 140 0.0008 nan 0.0500 -0.0000
## 160 0.0006 nan 0.0500 -0.0000
## 180 0.0004 nan 0.0500 0.0000
## 200 0.0003 nan 0.0500 0.0000
##
## - Fold19: shrinkage=0.05, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold19: shrinkage=0.10, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0378 nan 0.1000 0.0052
## 2 0.0334 nan 0.1000 0.0026
## 3 0.0303 nan 0.1000 0.0028
## 4 0.0264 nan 0.1000 0.0007
## 5 0.0241 nan 0.1000 0.0013
## 6 0.0212 nan 0.1000 0.0026
## 7 0.0192 nan 0.1000 -0.0000
## 8 0.0184 nan 0.1000 -0.0001
## 9 0.0170 nan 0.1000 0.0005
## 10 0.0158 nan 0.1000 0.0008
## 20 0.0069 nan 0.1000 -0.0000
## 40 0.0016 nan 0.1000 0.0000
## 60 0.0005 nan 0.1000 -0.0000
## 80 0.0002 nan 0.1000 -0.0000
## 100 0.0001 nan 0.1000 0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 0.0000
##
## - Fold19: shrinkage=0.10, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold19: shrinkage=0.10, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0374 nan 0.1000 0.0024
## 2 0.0333 nan 0.1000 0.0030
## 3 0.0312 nan 0.1000 -0.0011
## 4 0.0281 nan 0.1000 0.0034
## 5 0.0237 nan 0.1000 0.0036
## 6 0.0213 nan 0.1000 0.0023
## 7 0.0191 nan 0.1000 0.0020
## 8 0.0167 nan 0.1000 0.0019
## 9 0.0148 nan 0.1000 0.0004
## 10 0.0133 nan 0.1000 0.0013
## 20 0.0057 nan 0.1000 0.0005
## 40 0.0020 nan 0.1000 0.0000
## 60 0.0008 nan 0.1000 0.0000
## 80 0.0004 nan 0.1000 0.0000
## 100 0.0002 nan 0.1000 -0.0000
## 120 0.0001 nan 0.1000 0.0000
## 140 0.0001 nan 0.1000 0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 0.0000
##
## - Fold19: shrinkage=0.10, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold19: shrinkage=0.10, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0394 nan 0.1000 0.0029
## 2 0.0363 nan 0.1000 0.0012
## 3 0.0346 nan 0.1000 -0.0005
## 4 0.0311 nan 0.1000 0.0019
## 5 0.0272 nan 0.1000 0.0036
## 6 0.0251 nan 0.1000 0.0020
## 7 0.0218 nan 0.1000 0.0015
## 8 0.0198 nan 0.1000 0.0020
## 9 0.0178 nan 0.1000 0.0018
## 10 0.0155 nan 0.1000 0.0010
## 20 0.0091 nan 0.1000 0.0007
## 40 0.0042 nan 0.1000 -0.0000
## 60 0.0020 nan 0.1000 -0.0000
## 80 0.0011 nan 0.1000 0.0000
## 100 0.0006 nan 0.1000 -0.0000
## 120 0.0004 nan 0.1000 -0.0000
## 140 0.0003 nan 0.1000 0.0000
## 160 0.0002 nan 0.1000 -0.0000
## 180 0.0001 nan 0.1000 0.0000
## 200 0.0001 nan 0.1000 -0.0000
##
## - Fold19: shrinkage=0.10, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold19: shrinkage=0.10, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0371 nan 0.1000 0.0028
## 2 0.0323 nan 0.1000 0.0033
## 3 0.0274 nan 0.1000 0.0038
## 4 0.0244 nan 0.1000 0.0030
## 5 0.0211 nan 0.1000 0.0015
## 6 0.0193 nan 0.1000 0.0013
## 7 0.0168 nan 0.1000 0.0008
## 8 0.0146 nan 0.1000 0.0016
## 9 0.0127 nan 0.1000 0.0016
## 10 0.0112 nan 0.1000 0.0014
## 20 0.0032 nan 0.1000 0.0003
## 40 0.0006 nan 0.1000 -0.0001
## 60 0.0001 nan 0.1000 0.0000
## 80 0.0000 nan 0.1000 -0.0000
## 100 0.0000 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold19: shrinkage=0.10, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold19: shrinkage=0.10, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0377 nan 0.1000 0.0052
## 2 0.0323 nan 0.1000 0.0062
## 3 0.0299 nan 0.1000 -0.0002
## 4 0.0266 nan 0.1000 0.0029
## 5 0.0237 nan 0.1000 0.0026
## 6 0.0200 nan 0.1000 0.0021
## 7 0.0180 nan 0.1000 0.0012
## 8 0.0155 nan 0.1000 0.0008
## 9 0.0140 nan 0.1000 0.0007
## 10 0.0127 nan 0.1000 -0.0003
## 20 0.0047 nan 0.1000 -0.0000
## 40 0.0015 nan 0.1000 0.0000
## 60 0.0005 nan 0.1000 -0.0000
## 80 0.0002 nan 0.1000 0.0000
## 100 0.0001 nan 0.1000 0.0000
## 120 0.0001 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold19: shrinkage=0.10, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold19: shrinkage=0.10, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0373 nan 0.1000 0.0049
## 2 0.0348 nan 0.1000 -0.0009
## 3 0.0313 nan 0.1000 0.0040
## 4 0.0287 nan 0.1000 0.0025
## 5 0.0257 nan 0.1000 0.0031
## 6 0.0225 nan 0.1000 0.0028
## 7 0.0202 nan 0.1000 0.0015
## 8 0.0191 nan 0.1000 0.0008
## 9 0.0179 nan 0.1000 0.0015
## 10 0.0160 nan 0.1000 0.0010
## 20 0.0071 nan 0.1000 -0.0003
## 40 0.0029 nan 0.1000 0.0001
## 60 0.0013 nan 0.1000 0.0000
## 80 0.0009 nan 0.1000 -0.0000
## 100 0.0005 nan 0.1000 -0.0000
## 120 0.0003 nan 0.1000 -0.0000
## 140 0.0002 nan 0.1000 -0.0000
## 160 0.0001 nan 0.1000 -0.0000
## 180 0.0001 nan 0.1000 -0.0000
## 200 0.0001 nan 0.1000 -0.0000
##
## - Fold19: shrinkage=0.10, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold19: shrinkage=0.10, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0357 nan 0.1000 0.0066
## 2 0.0298 nan 0.1000 0.0060
## 3 0.0263 nan 0.1000 0.0023
## 4 0.0230 nan 0.1000 0.0032
## 5 0.0214 nan 0.1000 0.0005
## 6 0.0181 nan 0.1000 0.0022
## 7 0.0158 nan 0.1000 0.0017
## 8 0.0136 nan 0.1000 0.0017
## 9 0.0125 nan 0.1000 0.0001
## 10 0.0108 nan 0.1000 0.0003
## 20 0.0034 nan 0.1000 0.0004
## 40 0.0005 nan 0.1000 -0.0000
## 60 0.0001 nan 0.1000 -0.0000
## 80 0.0000 nan 0.1000 0.0000
## 100 0.0000 nan 0.1000 0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold19: shrinkage=0.10, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold19: shrinkage=0.10, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0394 nan 0.1000 0.0046
## 2 0.0381 nan 0.1000 -0.0006
## 3 0.0332 nan 0.1000 0.0052
## 4 0.0301 nan 0.1000 0.0007
## 5 0.0272 nan 0.1000 0.0032
## 6 0.0234 nan 0.1000 0.0009
## 7 0.0215 nan 0.1000 0.0014
## 8 0.0193 nan 0.1000 0.0019
## 9 0.0173 nan 0.1000 0.0022
## 10 0.0150 nan 0.1000 0.0020
## 20 0.0054 nan 0.1000 0.0003
## 40 0.0012 nan 0.1000 -0.0001
## 60 0.0005 nan 0.1000 -0.0000
## 80 0.0002 nan 0.1000 0.0000
## 100 0.0001 nan 0.1000 -0.0000
## 120 0.0001 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 0.0000
## 160 0.0000 nan 0.1000 0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold19: shrinkage=0.10, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold19: shrinkage=0.10, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0370 nan 0.1000 0.0048
## 2 0.0349 nan 0.1000 -0.0010
## 3 0.0307 nan 0.1000 0.0030
## 4 0.0273 nan 0.1000 0.0034
## 5 0.0237 nan 0.1000 0.0028
## 6 0.0224 nan 0.1000 0.0012
## 7 0.0198 nan 0.1000 0.0019
## 8 0.0178 nan 0.1000 0.0016
## 9 0.0165 nan 0.1000 0.0005
## 10 0.0158 nan 0.1000 0.0004
## 20 0.0083 nan 0.1000 -0.0000
## 40 0.0032 nan 0.1000 -0.0001
## 60 0.0016 nan 0.1000 -0.0001
## 80 0.0008 nan 0.1000 -0.0000
## 100 0.0004 nan 0.1000 0.0000
## 120 0.0002 nan 0.1000 -0.0000
## 140 0.0001 nan 0.1000 0.0000
## 160 0.0001 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold19: shrinkage=0.10, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold20: shrinkage=0.01, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0436 nan 0.0100 0.0002
## 2 0.0430 nan 0.0100 0.0004
## 3 0.0428 nan 0.0100 0.0001
## 4 0.0423 nan 0.0100 0.0001
## 5 0.0417 nan 0.0100 0.0006
## 6 0.0412 nan 0.0100 0.0004
## 7 0.0407 nan 0.0100 0.0004
## 8 0.0403 nan 0.0100 0.0005
## 9 0.0398 nan 0.0100 0.0002
## 10 0.0392 nan 0.0100 0.0005
## 20 0.0354 nan 0.0100 0.0004
## 40 0.0282 nan 0.0100 0.0003
## 60 0.0223 nan 0.0100 0.0003
## 80 0.0180 nan 0.0100 0.0002
## 100 0.0148 nan 0.0100 0.0000
## 120 0.0121 nan 0.0100 0.0001
## 140 0.0101 nan 0.0100 0.0000
## 160 0.0087 nan 0.0100 0.0000
## 180 0.0072 nan 0.0100 0.0000
## 200 0.0060 nan 0.0100 0.0001
##
## - Fold20: shrinkage=0.01, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold20: shrinkage=0.01, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0434 nan 0.0100 0.0005
## 2 0.0428 nan 0.0100 0.0007
## 3 0.0422 nan 0.0100 0.0004
## 4 0.0417 nan 0.0100 0.0006
## 5 0.0411 nan 0.0100 0.0003
## 6 0.0408 nan 0.0100 0.0004
## 7 0.0405 nan 0.0100 0.0002
## 8 0.0398 nan 0.0100 0.0006
## 9 0.0393 nan 0.0100 0.0004
## 10 0.0387 nan 0.0100 0.0002
## 20 0.0348 nan 0.0100 0.0003
## 40 0.0275 nan 0.0100 0.0003
## 60 0.0219 nan 0.0100 0.0002
## 80 0.0179 nan 0.0100 -0.0001
## 100 0.0145 nan 0.0100 0.0002
## 120 0.0119 nan 0.0100 0.0001
## 140 0.0099 nan 0.0100 0.0001
## 160 0.0084 nan 0.0100 0.0001
## 180 0.0071 nan 0.0100 -0.0000
## 200 0.0060 nan 0.0100 0.0000
##
## - Fold20: shrinkage=0.01, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold20: shrinkage=0.01, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0434 nan 0.0100 0.0005
## 2 0.0432 nan 0.0100 -0.0004
## 3 0.0426 nan 0.0100 0.0002
## 4 0.0420 nan 0.0100 0.0006
## 5 0.0417 nan 0.0100 0.0002
## 6 0.0413 nan 0.0100 0.0003
## 7 0.0409 nan 0.0100 0.0002
## 8 0.0404 nan 0.0100 0.0005
## 9 0.0400 nan 0.0100 0.0004
## 10 0.0395 nan 0.0100 0.0005
## 20 0.0349 nan 0.0100 0.0005
## 40 0.0281 nan 0.0100 0.0004
## 60 0.0226 nan 0.0100 0.0002
## 80 0.0189 nan 0.0100 0.0001
## 100 0.0164 nan 0.0100 0.0001
## 120 0.0140 nan 0.0100 0.0001
## 140 0.0120 nan 0.0100 0.0001
## 160 0.0105 nan 0.0100 0.0001
## 180 0.0092 nan 0.0100 0.0000
## 200 0.0082 nan 0.0100 0.0000
##
## - Fold20: shrinkage=0.01, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold20: shrinkage=0.01, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0435 nan 0.0100 0.0002
## 2 0.0428 nan 0.0100 0.0004
## 3 0.0422 nan 0.0100 0.0002
## 4 0.0413 nan 0.0100 0.0009
## 5 0.0408 nan 0.0100 -0.0001
## 6 0.0401 nan 0.0100 0.0002
## 7 0.0396 nan 0.0100 0.0004
## 8 0.0389 nan 0.0100 0.0004
## 9 0.0383 nan 0.0100 0.0006
## 10 0.0377 nan 0.0100 0.0003
## 20 0.0332 nan 0.0100 0.0003
## 40 0.0254 nan 0.0100 0.0003
## 60 0.0196 nan 0.0100 0.0002
## 80 0.0151 nan 0.0100 0.0000
## 100 0.0115 nan 0.0100 0.0000
## 120 0.0091 nan 0.0100 0.0000
## 140 0.0071 nan 0.0100 0.0001
## 160 0.0057 nan 0.0100 0.0000
## 180 0.0045 nan 0.0100 0.0000
## 200 0.0036 nan 0.0100 0.0000
##
## - Fold20: shrinkage=0.01, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold20: shrinkage=0.01, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0432 nan 0.0100 0.0005
## 2 0.0428 nan 0.0100 0.0001
## 3 0.0420 nan 0.0100 0.0006
## 4 0.0413 nan 0.0100 0.0002
## 5 0.0407 nan 0.0100 0.0004
## 6 0.0401 nan 0.0100 0.0004
## 7 0.0395 nan 0.0100 0.0006
## 8 0.0393 nan 0.0100 0.0001
## 9 0.0386 nan 0.0100 0.0006
## 10 0.0382 nan 0.0100 0.0003
## 20 0.0332 nan 0.0100 0.0005
## 40 0.0257 nan 0.0100 0.0004
## 60 0.0203 nan 0.0100 0.0003
## 80 0.0158 nan 0.0100 -0.0000
## 100 0.0125 nan 0.0100 0.0001
## 120 0.0102 nan 0.0100 0.0001
## 140 0.0083 nan 0.0100 0.0001
## 160 0.0068 nan 0.0100 0.0000
## 180 0.0056 nan 0.0100 0.0000
## 200 0.0046 nan 0.0100 0.0000
##
## - Fold20: shrinkage=0.01, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold20: shrinkage=0.01, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0435 nan 0.0100 0.0002
## 2 0.0432 nan 0.0100 0.0001
## 3 0.0426 nan 0.0100 0.0003
## 4 0.0422 nan 0.0100 0.0003
## 5 0.0416 nan 0.0100 0.0006
## 6 0.0410 nan 0.0100 0.0004
## 7 0.0405 nan 0.0100 0.0005
## 8 0.0401 nan 0.0100 0.0002
## 9 0.0396 nan 0.0100 0.0006
## 10 0.0391 nan 0.0100 0.0003
## 20 0.0349 nan 0.0100 0.0004
## 40 0.0279 nan 0.0100 0.0003
## 60 0.0226 nan 0.0100 0.0001
## 80 0.0185 nan 0.0100 0.0001
## 100 0.0155 nan 0.0100 0.0000
## 120 0.0132 nan 0.0100 0.0001
## 140 0.0111 nan 0.0100 0.0001
## 160 0.0097 nan 0.0100 0.0001
## 180 0.0086 nan 0.0100 0.0001
## 200 0.0076 nan 0.0100 0.0000
##
## - Fold20: shrinkage=0.01, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold20: shrinkage=0.01, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0432 nan 0.0100 0.0007
## 2 0.0426 nan 0.0100 0.0003
## 3 0.0422 nan 0.0100 0.0001
## 4 0.0418 nan 0.0100 0.0001
## 5 0.0414 nan 0.0100 0.0002
## 6 0.0408 nan 0.0100 0.0003
## 7 0.0400 nan 0.0100 0.0005
## 8 0.0395 nan 0.0100 0.0005
## 9 0.0391 nan 0.0100 0.0005
## 10 0.0385 nan 0.0100 0.0003
## 20 0.0327 nan 0.0100 0.0004
## 40 0.0248 nan 0.0100 0.0001
## 60 0.0192 nan 0.0100 0.0003
## 80 0.0147 nan 0.0100 0.0001
## 100 0.0114 nan 0.0100 0.0000
## 120 0.0090 nan 0.0100 0.0001
## 140 0.0067 nan 0.0100 0.0000
## 160 0.0053 nan 0.0100 0.0001
## 180 0.0043 nan 0.0100 -0.0000
## 200 0.0034 nan 0.0100 0.0000
##
## - Fold20: shrinkage=0.01, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold20: shrinkage=0.01, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0433 nan 0.0100 0.0005
## 2 0.0427 nan 0.0100 0.0006
## 3 0.0420 nan 0.0100 0.0005
## 4 0.0413 nan 0.0100 0.0005
## 5 0.0407 nan 0.0100 0.0002
## 6 0.0401 nan 0.0100 0.0003
## 7 0.0397 nan 0.0100 0.0001
## 8 0.0390 nan 0.0100 0.0004
## 9 0.0382 nan 0.0100 0.0004
## 10 0.0377 nan 0.0100 0.0004
## 20 0.0330 nan 0.0100 0.0003
## 40 0.0251 nan 0.0100 0.0003
## 60 0.0194 nan 0.0100 0.0003
## 80 0.0154 nan 0.0100 -0.0000
## 100 0.0120 nan 0.0100 -0.0000
## 120 0.0097 nan 0.0100 0.0001
## 140 0.0078 nan 0.0100 0.0001
## 160 0.0061 nan 0.0100 0.0000
## 180 0.0050 nan 0.0100 0.0000
## 200 0.0041 nan 0.0100 0.0000
##
## - Fold20: shrinkage=0.01, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold20: shrinkage=0.01, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0434 nan 0.0100 0.0004
## 2 0.0428 nan 0.0100 0.0005
## 3 0.0422 nan 0.0100 0.0005
## 4 0.0420 nan 0.0100 -0.0000
## 5 0.0415 nan 0.0100 0.0005
## 6 0.0411 nan 0.0100 0.0004
## 7 0.0406 nan 0.0100 0.0005
## 8 0.0403 nan 0.0100 0.0000
## 9 0.0398 nan 0.0100 0.0006
## 10 0.0392 nan 0.0100 0.0005
## 20 0.0350 nan 0.0100 0.0005
## 40 0.0280 nan 0.0100 0.0003
## 60 0.0228 nan 0.0100 0.0000
## 80 0.0194 nan 0.0100 0.0001
## 100 0.0164 nan 0.0100 0.0001
## 120 0.0142 nan 0.0100 0.0000
## 140 0.0122 nan 0.0100 0.0000
## 160 0.0106 nan 0.0100 0.0001
## 180 0.0093 nan 0.0100 0.0001
## 200 0.0084 nan 0.0100 0.0000
##
## - Fold20: shrinkage=0.01, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold20: shrinkage=0.05, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0408 nan 0.0500 0.0030
## 2 0.0385 nan 0.0500 0.0008
## 3 0.0373 nan 0.0500 0.0004
## 4 0.0351 nan 0.0500 0.0024
## 5 0.0343 nan 0.0500 -0.0004
## 6 0.0326 nan 0.0500 0.0020
## 7 0.0306 nan 0.0500 0.0013
## 8 0.0278 nan 0.0500 0.0022
## 9 0.0258 nan 0.0500 0.0011
## 10 0.0252 nan 0.0500 0.0002
## 20 0.0144 nan 0.0500 0.0001
## 40 0.0064 nan 0.0500 0.0003
## 60 0.0027 nan 0.0500 0.0000
## 80 0.0015 nan 0.0500 0.0000
## 100 0.0009 nan 0.0500 0.0000
## 120 0.0005 nan 0.0500 -0.0000
## 140 0.0003 nan 0.0500 0.0000
## 160 0.0002 nan 0.0500 -0.0000
## 180 0.0001 nan 0.0500 -0.0000
## 200 0.0001 nan 0.0500 0.0000
##
## - Fold20: shrinkage=0.05, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold20: shrinkage=0.05, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0414 nan 0.0500 0.0019
## 2 0.0386 nan 0.0500 0.0030
## 3 0.0359 nan 0.0500 0.0025
## 4 0.0341 nan 0.0500 0.0006
## 5 0.0315 nan 0.0500 0.0013
## 6 0.0295 nan 0.0500 0.0018
## 7 0.0278 nan 0.0500 0.0015
## 8 0.0263 nan 0.0500 0.0011
## 9 0.0248 nan 0.0500 0.0016
## 10 0.0235 nan 0.0500 0.0012
## 20 0.0143 nan 0.0500 0.0002
## 40 0.0058 nan 0.0500 0.0002
## 60 0.0029 nan 0.0500 -0.0000
## 80 0.0016 nan 0.0500 0.0000
## 100 0.0009 nan 0.0500 -0.0000
## 120 0.0006 nan 0.0500 -0.0000
## 140 0.0003 nan 0.0500 -0.0000
## 160 0.0002 nan 0.0500 0.0000
## 180 0.0002 nan 0.0500 0.0000
## 200 0.0001 nan 0.0500 -0.0000
##
## - Fold20: shrinkage=0.05, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold20: shrinkage=0.05, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0407 nan 0.0500 0.0030
## 2 0.0376 nan 0.0500 0.0028
## 3 0.0354 nan 0.0500 0.0022
## 4 0.0330 nan 0.0500 0.0020
## 5 0.0310 nan 0.0500 0.0021
## 6 0.0297 nan 0.0500 0.0015
## 7 0.0281 nan 0.0500 0.0015
## 8 0.0270 nan 0.0500 -0.0002
## 9 0.0256 nan 0.0500 0.0015
## 10 0.0246 nan 0.0500 0.0007
## 20 0.0168 nan 0.0500 0.0003
## 40 0.0092 nan 0.0500 -0.0000
## 60 0.0055 nan 0.0500 -0.0001
## 80 0.0038 nan 0.0500 -0.0000
## 100 0.0024 nan 0.0500 -0.0000
## 120 0.0017 nan 0.0500 0.0000
## 140 0.0013 nan 0.0500 -0.0000
## 160 0.0010 nan 0.0500 0.0000
## 180 0.0008 nan 0.0500 -0.0000
## 200 0.0006 nan 0.0500 -0.0000
##
## - Fold20: shrinkage=0.05, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold20: shrinkage=0.05, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0404 nan 0.0500 0.0033
## 2 0.0368 nan 0.0500 0.0020
## 3 0.0344 nan 0.0500 0.0015
## 4 0.0319 nan 0.0500 0.0024
## 5 0.0307 nan 0.0500 0.0002
## 6 0.0287 nan 0.0500 0.0019
## 7 0.0267 nan 0.0500 0.0015
## 8 0.0247 nan 0.0500 0.0013
## 9 0.0231 nan 0.0500 0.0014
## 10 0.0218 nan 0.0500 0.0009
## 20 0.0120 nan 0.0500 0.0000
## 40 0.0047 nan 0.0500 -0.0001
## 60 0.0019 nan 0.0500 -0.0000
## 80 0.0009 nan 0.0500 0.0000
## 100 0.0004 nan 0.0500 0.0000
## 120 0.0002 nan 0.0500 -0.0000
## 140 0.0001 nan 0.0500 -0.0000
## 160 0.0000 nan 0.0500 -0.0000
## 180 0.0000 nan 0.0500 -0.0000
## 200 0.0000 nan 0.0500 -0.0000
##
## - Fold20: shrinkage=0.05, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold20: shrinkage=0.05, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0405 nan 0.0500 0.0036
## 2 0.0373 nan 0.0500 0.0021
## 3 0.0355 nan 0.0500 0.0020
## 4 0.0331 nan 0.0500 0.0018
## 5 0.0310 nan 0.0500 0.0023
## 6 0.0288 nan 0.0500 0.0018
## 7 0.0268 nan 0.0500 0.0018
## 8 0.0249 nan 0.0500 0.0006
## 9 0.0231 nan 0.0500 0.0013
## 10 0.0226 nan 0.0500 -0.0002
## 20 0.0118 nan 0.0500 0.0000
## 40 0.0039 nan 0.0500 0.0002
## 60 0.0016 nan 0.0500 -0.0000
## 80 0.0008 nan 0.0500 -0.0000
## 100 0.0005 nan 0.0500 0.0000
## 120 0.0003 nan 0.0500 -0.0000
## 140 0.0002 nan 0.0500 -0.0000
## 160 0.0001 nan 0.0500 -0.0000
## 180 0.0001 nan 0.0500 0.0000
## 200 0.0001 nan 0.0500 0.0000
##
## - Fold20: shrinkage=0.05, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold20: shrinkage=0.05, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0409 nan 0.0500 0.0031
## 2 0.0392 nan 0.0500 0.0007
## 3 0.0379 nan 0.0500 0.0008
## 4 0.0347 nan 0.0500 0.0025
## 5 0.0332 nan 0.0500 0.0012
## 6 0.0315 nan 0.0500 0.0002
## 7 0.0293 nan 0.0500 0.0012
## 8 0.0284 nan 0.0500 0.0006
## 9 0.0266 nan 0.0500 0.0017
## 10 0.0255 nan 0.0500 0.0001
## 20 0.0167 nan 0.0500 0.0007
## 40 0.0087 nan 0.0500 0.0001
## 60 0.0055 nan 0.0500 0.0001
## 80 0.0037 nan 0.0500 -0.0000
## 100 0.0027 nan 0.0500 -0.0000
## 120 0.0023 nan 0.0500 -0.0000
## 140 0.0016 nan 0.0500 -0.0000
## 160 0.0013 nan 0.0500 -0.0000
## 180 0.0010 nan 0.0500 -0.0000
## 200 0.0009 nan 0.0500 -0.0000
##
## - Fold20: shrinkage=0.05, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold20: shrinkage=0.05, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0407 nan 0.0500 0.0034
## 2 0.0375 nan 0.0500 0.0023
## 3 0.0348 nan 0.0500 0.0024
## 4 0.0333 nan 0.0500 0.0012
## 5 0.0310 nan 0.0500 0.0015
## 6 0.0293 nan 0.0500 0.0006
## 7 0.0268 nan 0.0500 0.0012
## 8 0.0246 nan 0.0500 0.0017
## 9 0.0227 nan 0.0500 0.0009
## 10 0.0211 nan 0.0500 0.0008
## 20 0.0113 nan 0.0500 0.0006
## 40 0.0035 nan 0.0500 0.0000
## 60 0.0013 nan 0.0500 -0.0000
## 80 0.0005 nan 0.0500 -0.0000
## 100 0.0002 nan 0.0500 0.0000
## 120 0.0001 nan 0.0500 -0.0000
## 140 0.0000 nan 0.0500 -0.0000
## 160 0.0000 nan 0.0500 -0.0000
## 180 0.0000 nan 0.0500 0.0000
## 200 0.0000 nan 0.0500 -0.0000
##
## - Fold20: shrinkage=0.05, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold20: shrinkage=0.05, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0395 nan 0.0500 0.0034
## 2 0.0380 nan 0.0500 0.0006
## 3 0.0347 nan 0.0500 0.0018
## 4 0.0341 nan 0.0500 -0.0002
## 5 0.0319 nan 0.0500 0.0019
## 6 0.0294 nan 0.0500 0.0007
## 7 0.0269 nan 0.0500 0.0022
## 8 0.0253 nan 0.0500 0.0010
## 9 0.0241 nan 0.0500 0.0008
## 10 0.0227 nan 0.0500 0.0008
## 20 0.0114 nan 0.0500 0.0005
## 40 0.0039 nan 0.0500 0.0001
## 60 0.0014 nan 0.0500 0.0000
## 80 0.0009 nan 0.0500 0.0000
## 100 0.0006 nan 0.0500 -0.0000
## 120 0.0004 nan 0.0500 -0.0000
## 140 0.0002 nan 0.0500 -0.0000
## 160 0.0001 nan 0.0500 0.0000
## 180 0.0001 nan 0.0500 0.0000
## 200 0.0001 nan 0.0500 -0.0000
##
## - Fold20: shrinkage=0.05, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold20: shrinkage=0.05, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0407 nan 0.0500 0.0017
## 2 0.0381 nan 0.0500 0.0024
## 3 0.0355 nan 0.0500 0.0025
## 4 0.0332 nan 0.0500 0.0022
## 5 0.0323 nan 0.0500 0.0001
## 6 0.0303 nan 0.0500 0.0003
## 7 0.0283 nan 0.0500 0.0019
## 8 0.0268 nan 0.0500 0.0011
## 9 0.0254 nan 0.0500 0.0015
## 10 0.0245 nan 0.0500 0.0005
## 20 0.0158 nan 0.0500 0.0001
## 40 0.0083 nan 0.0500 0.0002
## 60 0.0052 nan 0.0500 0.0001
## 80 0.0035 nan 0.0500 -0.0001
## 100 0.0025 nan 0.0500 -0.0000
## 120 0.0016 nan 0.0500 -0.0000
## 140 0.0011 nan 0.0500 -0.0000
## 160 0.0008 nan 0.0500 -0.0000
## 180 0.0006 nan 0.0500 -0.0000
## 200 0.0004 nan 0.0500 -0.0000
##
## - Fold20: shrinkage=0.05, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold20: shrinkage=0.10, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0414 nan 0.1000 -0.0021
## 2 0.0368 nan 0.1000 0.0050
## 3 0.0318 nan 0.1000 0.0037
## 4 0.0289 nan 0.1000 0.0024
## 5 0.0258 nan 0.1000 0.0012
## 6 0.0235 nan 0.1000 0.0030
## 7 0.0215 nan 0.1000 -0.0007
## 8 0.0188 nan 0.1000 0.0012
## 9 0.0164 nan 0.1000 0.0016
## 10 0.0147 nan 0.1000 0.0011
## 20 0.0068 nan 0.1000 0.0003
## 40 0.0020 nan 0.1000 -0.0000
## 60 0.0007 nan 0.1000 -0.0000
## 80 0.0003 nan 0.1000 0.0000
## 100 0.0001 nan 0.1000 -0.0000
## 120 0.0001 nan 0.1000 0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 0.0000
##
## - Fold20: shrinkage=0.10, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold20: shrinkage=0.10, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0416 nan 0.1000 0.0001
## 2 0.0365 nan 0.1000 0.0035
## 3 0.0314 nan 0.1000 0.0039
## 4 0.0276 nan 0.1000 0.0039
## 5 0.0246 nan 0.1000 0.0028
## 6 0.0216 nan 0.1000 0.0028
## 7 0.0199 nan 0.1000 0.0012
## 8 0.0177 nan 0.1000 0.0019
## 9 0.0154 nan 0.1000 0.0014
## 10 0.0135 nan 0.1000 0.0016
## 20 0.0052 nan 0.1000 -0.0001
## 40 0.0012 nan 0.1000 -0.0000
## 60 0.0004 nan 0.1000 -0.0000
## 80 0.0002 nan 0.1000 -0.0000
## 100 0.0001 nan 0.1000 0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold20: shrinkage=0.10, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold20: shrinkage=0.10, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0397 nan 0.1000 0.0035
## 2 0.0364 nan 0.1000 0.0007
## 3 0.0312 nan 0.1000 0.0043
## 4 0.0285 nan 0.1000 0.0026
## 5 0.0249 nan 0.1000 0.0020
## 6 0.0234 nan 0.1000 0.0005
## 7 0.0223 nan 0.1000 -0.0010
## 8 0.0203 nan 0.1000 0.0023
## 9 0.0187 nan 0.1000 0.0008
## 10 0.0174 nan 0.1000 0.0005
## 20 0.0074 nan 0.1000 0.0006
## 40 0.0033 nan 0.1000 0.0001
## 60 0.0021 nan 0.1000 0.0001
## 80 0.0011 nan 0.1000 -0.0000
## 100 0.0006 nan 0.1000 -0.0000
## 120 0.0003 nan 0.1000 -0.0000
## 140 0.0002 nan 0.1000 -0.0000
## 160 0.0001 nan 0.1000 -0.0000
## 180 0.0001 nan 0.1000 -0.0000
## 200 0.0001 nan 0.1000 -0.0000
##
## - Fold20: shrinkage=0.10, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold20: shrinkage=0.10, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0376 nan 0.1000 0.0039
## 2 0.0326 nan 0.1000 0.0030
## 3 0.0301 nan 0.1000 0.0005
## 4 0.0282 nan 0.1000 -0.0007
## 5 0.0248 nan 0.1000 0.0034
## 6 0.0217 nan 0.1000 0.0026
## 7 0.0185 nan 0.1000 0.0021
## 8 0.0158 nan 0.1000 0.0026
## 9 0.0144 nan 0.1000 0.0014
## 10 0.0120 nan 0.1000 0.0016
## 20 0.0038 nan 0.1000 0.0002
## 40 0.0006 nan 0.1000 0.0000
## 60 0.0002 nan 0.1000 0.0000
## 80 0.0000 nan 0.1000 -0.0000
## 100 0.0000 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold20: shrinkage=0.10, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold20: shrinkage=0.10, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0371 nan 0.1000 0.0033
## 2 0.0319 nan 0.1000 0.0053
## 3 0.0272 nan 0.1000 0.0033
## 4 0.0258 nan 0.1000 0.0001
## 5 0.0227 nan 0.1000 0.0034
## 6 0.0197 nan 0.1000 0.0004
## 7 0.0175 nan 0.1000 0.0021
## 8 0.0156 nan 0.1000 0.0015
## 9 0.0136 nan 0.1000 0.0007
## 10 0.0118 nan 0.1000 0.0015
## 20 0.0036 nan 0.1000 0.0000
## 40 0.0008 nan 0.1000 -0.0001
## 60 0.0003 nan 0.1000 0.0000
## 80 0.0001 nan 0.1000 -0.0000
## 100 0.0000 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold20: shrinkage=0.10, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold20: shrinkage=0.10, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0388 nan 0.1000 0.0055
## 2 0.0332 nan 0.1000 0.0034
## 3 0.0300 nan 0.1000 0.0033
## 4 0.0274 nan 0.1000 0.0021
## 5 0.0237 nan 0.1000 0.0022
## 6 0.0226 nan 0.1000 0.0003
## 7 0.0213 nan 0.1000 0.0008
## 8 0.0192 nan 0.1000 0.0019
## 9 0.0175 nan 0.1000 0.0014
## 10 0.0159 nan 0.1000 0.0016
## 20 0.0079 nan 0.1000 0.0004
## 40 0.0038 nan 0.1000 -0.0001
## 60 0.0020 nan 0.1000 -0.0001
## 80 0.0011 nan 0.1000 -0.0001
## 100 0.0008 nan 0.1000 -0.0000
## 120 0.0004 nan 0.1000 -0.0000
## 140 0.0002 nan 0.1000 -0.0000
## 160 0.0002 nan 0.1000 -0.0000
## 180 0.0001 nan 0.1000 -0.0000
## 200 0.0001 nan 0.1000 -0.0000
##
## - Fold20: shrinkage=0.10, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold20: shrinkage=0.10, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0384 nan 0.1000 0.0016
## 2 0.0355 nan 0.1000 -0.0004
## 3 0.0299 nan 0.1000 0.0044
## 4 0.0256 nan 0.1000 0.0025
## 5 0.0215 nan 0.1000 0.0021
## 6 0.0190 nan 0.1000 0.0019
## 7 0.0160 nan 0.1000 0.0018
## 8 0.0139 nan 0.1000 0.0013
## 9 0.0115 nan 0.1000 0.0013
## 10 0.0104 nan 0.1000 0.0005
## 20 0.0029 nan 0.1000 -0.0001
## 40 0.0005 nan 0.1000 -0.0000
## 60 0.0001 nan 0.1000 -0.0000
## 80 0.0000 nan 0.1000 0.0000
## 100 0.0000 nan 0.1000 0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 0.0000
## 180 0.0000 nan 0.1000 0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold20: shrinkage=0.10, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold20: shrinkage=0.10, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0386 nan 0.1000 0.0054
## 2 0.0345 nan 0.1000 -0.0004
## 3 0.0294 nan 0.1000 0.0026
## 4 0.0254 nan 0.1000 0.0029
## 5 0.0222 nan 0.1000 0.0029
## 6 0.0190 nan 0.1000 0.0016
## 7 0.0174 nan 0.1000 0.0013
## 8 0.0150 nan 0.1000 0.0005
## 9 0.0126 nan 0.1000 0.0016
## 10 0.0112 nan 0.1000 0.0006
## 20 0.0041 nan 0.1000 0.0003
## 40 0.0010 nan 0.1000 0.0000
## 60 0.0003 nan 0.1000 -0.0000
## 80 0.0002 nan 0.1000 -0.0000
## 100 0.0001 nan 0.1000 -0.0000
## 120 0.0001 nan 0.1000 0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold20: shrinkage=0.10, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold20: shrinkage=0.10, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0399 nan 0.1000 0.0031
## 2 0.0347 nan 0.1000 0.0051
## 3 0.0318 nan 0.1000 0.0034
## 4 0.0283 nan 0.1000 0.0035
## 5 0.0261 nan 0.1000 0.0018
## 6 0.0237 nan 0.1000 0.0008
## 7 0.0212 nan 0.1000 0.0020
## 8 0.0194 nan 0.1000 0.0016
## 9 0.0175 nan 0.1000 0.0002
## 10 0.0172 nan 0.1000 -0.0015
## 20 0.0102 nan 0.1000 0.0003
## 40 0.0041 nan 0.1000 0.0002
## 60 0.0026 nan 0.1000 -0.0001
## 80 0.0012 nan 0.1000 -0.0001
## 100 0.0008 nan 0.1000 -0.0000
## 120 0.0004 nan 0.1000 0.0000
## 140 0.0003 nan 0.1000 -0.0000
## 160 0.0002 nan 0.1000 -0.0000
## 180 0.0001 nan 0.1000 -0.0000
## 200 0.0001 nan 0.1000 -0.0000
##
## - Fold20: shrinkage=0.10, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold21: shrinkage=0.01, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0415 nan 0.0100 0.0005
## 2 0.0407 nan 0.0100 0.0006
## 3 0.0403 nan 0.0100 0.0002
## 4 0.0398 nan 0.0100 0.0005
## 5 0.0393 nan 0.0100 0.0005
## 6 0.0388 nan 0.0100 0.0004
## 7 0.0383 nan 0.0100 0.0004
## 8 0.0378 nan 0.0100 0.0004
## 9 0.0373 nan 0.0100 0.0005
## 10 0.0368 nan 0.0100 0.0005
## 20 0.0324 nan 0.0100 0.0004
## 40 0.0261 nan 0.0100 0.0002
## 60 0.0203 nan 0.0100 0.0003
## 80 0.0165 nan 0.0100 0.0001
## 100 0.0136 nan 0.0100 0.0001
## 120 0.0113 nan 0.0100 0.0001
## 140 0.0092 nan 0.0100 -0.0000
## 160 0.0079 nan 0.0100 -0.0000
## 180 0.0067 nan 0.0100 0.0001
## 200 0.0058 nan 0.0100 0.0000
##
## - Fold21: shrinkage=0.01, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold21: shrinkage=0.01, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0414 nan 0.0100 0.0006
## 2 0.0409 nan 0.0100 0.0004
## 3 0.0404 nan 0.0100 0.0005
## 4 0.0398 nan 0.0100 0.0004
## 5 0.0393 nan 0.0100 0.0003
## 6 0.0387 nan 0.0100 0.0004
## 7 0.0381 nan 0.0100 0.0005
## 8 0.0377 nan 0.0100 0.0005
## 9 0.0373 nan 0.0100 0.0002
## 10 0.0369 nan 0.0100 0.0004
## 20 0.0326 nan 0.0100 0.0000
## 40 0.0260 nan 0.0100 -0.0001
## 60 0.0213 nan 0.0100 0.0002
## 80 0.0177 nan 0.0100 0.0001
## 100 0.0145 nan 0.0100 0.0001
## 120 0.0122 nan 0.0100 0.0001
## 140 0.0102 nan 0.0100 0.0001
## 160 0.0089 nan 0.0100 0.0000
## 180 0.0075 nan 0.0100 0.0001
## 200 0.0065 nan 0.0100 0.0000
##
## - Fold21: shrinkage=0.01, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold21: shrinkage=0.01, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0414 nan 0.0100 0.0005
## 2 0.0409 nan 0.0100 0.0006
## 3 0.0405 nan 0.0100 0.0002
## 4 0.0400 nan 0.0100 0.0004
## 5 0.0396 nan 0.0100 0.0004
## 6 0.0392 nan 0.0100 0.0004
## 7 0.0389 nan 0.0100 0.0001
## 8 0.0385 nan 0.0100 0.0004
## 9 0.0379 nan 0.0100 0.0004
## 10 0.0375 nan 0.0100 0.0004
## 20 0.0337 nan 0.0100 0.0002
## 40 0.0274 nan 0.0100 0.0003
## 60 0.0226 nan 0.0100 0.0001
## 80 0.0189 nan 0.0100 0.0001
## 100 0.0158 nan 0.0100 0.0002
## 120 0.0136 nan 0.0100 -0.0001
## 140 0.0120 nan 0.0100 0.0001
## 160 0.0104 nan 0.0100 -0.0000
## 180 0.0092 nan 0.0100 0.0000
## 200 0.0081 nan 0.0100 0.0000
##
## - Fold21: shrinkage=0.01, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold21: shrinkage=0.01, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0415 nan 0.0100 0.0003
## 2 0.0410 nan 0.0100 0.0005
## 3 0.0403 nan 0.0100 0.0004
## 4 0.0399 nan 0.0100 0.0001
## 5 0.0395 nan 0.0100 0.0003
## 6 0.0391 nan 0.0100 0.0000
## 7 0.0383 nan 0.0100 0.0007
## 8 0.0378 nan 0.0100 0.0005
## 9 0.0370 nan 0.0100 0.0007
## 10 0.0366 nan 0.0100 0.0005
## 20 0.0314 nan 0.0100 0.0003
## 40 0.0240 nan 0.0100 0.0003
## 60 0.0184 nan 0.0100 0.0001
## 80 0.0140 nan 0.0100 0.0001
## 100 0.0111 nan 0.0100 0.0002
## 120 0.0089 nan 0.0100 0.0001
## 140 0.0072 nan 0.0100 0.0000
## 160 0.0058 nan 0.0100 0.0000
## 180 0.0048 nan 0.0100 0.0000
## 200 0.0039 nan 0.0100 0.0000
##
## - Fold21: shrinkage=0.01, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold21: shrinkage=0.01, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0414 nan 0.0100 0.0004
## 2 0.0409 nan 0.0100 0.0004
## 3 0.0403 nan 0.0100 0.0005
## 4 0.0398 nan 0.0100 0.0004
## 5 0.0391 nan 0.0100 0.0004
## 6 0.0384 nan 0.0100 0.0004
## 7 0.0378 nan 0.0100 0.0006
## 8 0.0373 nan 0.0100 0.0004
## 9 0.0366 nan 0.0100 0.0005
## 10 0.0361 nan 0.0100 0.0000
## 20 0.0316 nan 0.0100 0.0004
## 40 0.0254 nan 0.0100 -0.0000
## 60 0.0197 nan 0.0100 0.0002
## 80 0.0154 nan 0.0100 0.0001
## 100 0.0123 nan 0.0100 0.0001
## 120 0.0101 nan 0.0100 0.0000
## 140 0.0083 nan 0.0100 0.0001
## 160 0.0068 nan 0.0100 0.0001
## 180 0.0058 nan 0.0100 0.0000
## 200 0.0048 nan 0.0100 0.0000
##
## - Fold21: shrinkage=0.01, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold21: shrinkage=0.01, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0412 nan 0.0100 0.0005
## 2 0.0407 nan 0.0100 0.0005
## 3 0.0403 nan 0.0100 0.0003
## 4 0.0400 nan 0.0100 0.0003
## 5 0.0395 nan 0.0100 0.0003
## 6 0.0389 nan 0.0100 0.0004
## 7 0.0384 nan 0.0100 0.0005
## 8 0.0380 nan 0.0100 0.0002
## 9 0.0378 nan 0.0100 0.0001
## 10 0.0374 nan 0.0100 0.0002
## 20 0.0334 nan 0.0100 0.0001
## 40 0.0269 nan 0.0100 0.0003
## 60 0.0223 nan 0.0100 0.0002
## 80 0.0188 nan 0.0100 0.0001
## 100 0.0162 nan 0.0100 0.0001
## 120 0.0141 nan 0.0100 0.0001
## 140 0.0121 nan 0.0100 0.0001
## 160 0.0106 nan 0.0100 -0.0001
## 180 0.0093 nan 0.0100 0.0001
## 200 0.0082 nan 0.0100 0.0000
##
## - Fold21: shrinkage=0.01, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold21: shrinkage=0.01, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0416 nan 0.0100 0.0003
## 2 0.0410 nan 0.0100 0.0006
## 3 0.0404 nan 0.0100 0.0005
## 4 0.0398 nan 0.0100 0.0005
## 5 0.0391 nan 0.0100 0.0005
## 6 0.0384 nan 0.0100 0.0009
## 7 0.0380 nan 0.0100 0.0002
## 8 0.0374 nan 0.0100 0.0007
## 9 0.0367 nan 0.0100 0.0005
## 10 0.0361 nan 0.0100 0.0003
## 20 0.0309 nan 0.0100 0.0002
## 40 0.0225 nan 0.0100 0.0002
## 60 0.0171 nan 0.0100 0.0002
## 80 0.0131 nan 0.0100 0.0001
## 100 0.0103 nan 0.0100 0.0001
## 120 0.0083 nan 0.0100 0.0000
## 140 0.0066 nan 0.0100 0.0001
## 160 0.0052 nan 0.0100 0.0000
## 180 0.0043 nan 0.0100 0.0000
## 200 0.0033 nan 0.0100 0.0000
##
## - Fold21: shrinkage=0.01, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold21: shrinkage=0.01, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0414 nan 0.0100 0.0006
## 2 0.0408 nan 0.0100 0.0005
## 3 0.0401 nan 0.0100 0.0005
## 4 0.0396 nan 0.0100 0.0004
## 5 0.0389 nan 0.0100 0.0004
## 6 0.0383 nan 0.0100 0.0005
## 7 0.0376 nan 0.0100 0.0006
## 8 0.0372 nan 0.0100 0.0005
## 9 0.0368 nan 0.0100 0.0003
## 10 0.0362 nan 0.0100 0.0003
## 20 0.0312 nan 0.0100 0.0004
## 40 0.0236 nan 0.0100 0.0002
## 60 0.0179 nan 0.0100 0.0002
## 80 0.0139 nan 0.0100 0.0001
## 100 0.0112 nan 0.0100 0.0002
## 120 0.0092 nan 0.0100 0.0001
## 140 0.0074 nan 0.0100 0.0000
## 160 0.0059 nan 0.0100 -0.0000
## 180 0.0050 nan 0.0100 0.0000
## 200 0.0042 nan 0.0100 -0.0000
##
## - Fold21: shrinkage=0.01, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold21: shrinkage=0.01, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0416 nan 0.0100 0.0003
## 2 0.0410 nan 0.0100 0.0005
## 3 0.0404 nan 0.0100 0.0006
## 4 0.0401 nan 0.0100 0.0004
## 5 0.0397 nan 0.0100 0.0001
## 6 0.0393 nan 0.0100 0.0002
## 7 0.0389 nan 0.0100 0.0003
## 8 0.0385 nan 0.0100 0.0003
## 9 0.0380 nan 0.0100 0.0002
## 10 0.0375 nan 0.0100 0.0004
## 20 0.0335 nan 0.0100 0.0002
## 40 0.0275 nan 0.0100 0.0002
## 60 0.0223 nan 0.0100 0.0001
## 80 0.0189 nan 0.0100 -0.0001
## 100 0.0160 nan 0.0100 0.0001
## 120 0.0137 nan 0.0100 0.0000
## 140 0.0120 nan 0.0100 -0.0000
## 160 0.0105 nan 0.0100 0.0001
## 180 0.0094 nan 0.0100 0.0001
## 200 0.0085 nan 0.0100 0.0000
##
## - Fold21: shrinkage=0.01, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold21: shrinkage=0.05, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0397 nan 0.0500 0.0018
## 2 0.0379 nan 0.0500 0.0006
## 3 0.0353 nan 0.0500 0.0018
## 4 0.0335 nan 0.0500 0.0016
## 5 0.0312 nan 0.0500 0.0013
## 6 0.0303 nan 0.0500 0.0001
## 7 0.0298 nan 0.0500 -0.0001
## 8 0.0287 nan 0.0500 0.0004
## 9 0.0270 nan 0.0500 0.0016
## 10 0.0263 nan 0.0500 -0.0005
## 20 0.0147 nan 0.0500 0.0006
## 40 0.0068 nan 0.0500 -0.0000
## 60 0.0035 nan 0.0500 0.0001
## 80 0.0019 nan 0.0500 0.0000
## 100 0.0012 nan 0.0500 -0.0001
## 120 0.0007 nan 0.0500 -0.0000
## 140 0.0004 nan 0.0500 -0.0000
## 160 0.0003 nan 0.0500 -0.0000
## 180 0.0002 nan 0.0500 0.0000
## 200 0.0001 nan 0.0500 -0.0000
##
## - Fold21: shrinkage=0.05, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold21: shrinkage=0.05, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0401 nan 0.0500 0.0010
## 2 0.0377 nan 0.0500 0.0027
## 3 0.0352 nan 0.0500 0.0011
## 4 0.0329 nan 0.0500 0.0014
## 5 0.0309 nan 0.0500 0.0017
## 6 0.0290 nan 0.0500 0.0013
## 7 0.0285 nan 0.0500 -0.0004
## 8 0.0269 nan 0.0500 0.0016
## 9 0.0258 nan 0.0500 0.0006
## 10 0.0246 nan 0.0500 0.0011
## 20 0.0155 nan 0.0500 -0.0007
## 40 0.0062 nan 0.0500 0.0001
## 60 0.0034 nan 0.0500 -0.0000
## 80 0.0021 nan 0.0500 -0.0000
## 100 0.0012 nan 0.0500 -0.0001
## 120 0.0008 nan 0.0500 0.0000
## 140 0.0006 nan 0.0500 -0.0000
## 160 0.0004 nan 0.0500 -0.0000
## 180 0.0003 nan 0.0500 -0.0000
## 200 0.0002 nan 0.0500 -0.0000
##
## - Fold21: shrinkage=0.05, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold21: shrinkage=0.05, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0387 nan 0.0500 0.0027
## 2 0.0374 nan 0.0500 0.0004
## 3 0.0360 nan 0.0500 0.0003
## 4 0.0336 nan 0.0500 0.0018
## 5 0.0322 nan 0.0500 -0.0002
## 6 0.0305 nan 0.0500 0.0018
## 7 0.0287 nan 0.0500 0.0009
## 8 0.0271 nan 0.0500 0.0017
## 9 0.0254 nan 0.0500 0.0013
## 10 0.0239 nan 0.0500 0.0011
## 20 0.0153 nan 0.0500 0.0001
## 40 0.0077 nan 0.0500 0.0002
## 60 0.0045 nan 0.0500 -0.0001
## 80 0.0031 nan 0.0500 -0.0000
## 100 0.0020 nan 0.0500 -0.0000
## 120 0.0017 nan 0.0500 -0.0000
## 140 0.0012 nan 0.0500 -0.0000
## 160 0.0009 nan 0.0500 -0.0000
## 180 0.0006 nan 0.0500 0.0000
## 200 0.0005 nan 0.0500 -0.0000
##
## - Fold21: shrinkage=0.05, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold21: shrinkage=0.05, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0389 nan 0.0500 0.0016
## 2 0.0363 nan 0.0500 0.0023
## 3 0.0342 nan 0.0500 0.0022
## 4 0.0316 nan 0.0500 0.0021
## 5 0.0291 nan 0.0500 0.0016
## 6 0.0271 nan 0.0500 0.0015
## 7 0.0249 nan 0.0500 0.0016
## 8 0.0231 nan 0.0500 0.0013
## 9 0.0219 nan 0.0500 0.0006
## 10 0.0203 nan 0.0500 0.0009
## 20 0.0102 nan 0.0500 0.0005
## 40 0.0034 nan 0.0500 0.0000
## 60 0.0013 nan 0.0500 -0.0000
## 80 0.0006 nan 0.0500 -0.0000
## 100 0.0003 nan 0.0500 -0.0000
## 120 0.0002 nan 0.0500 -0.0000
## 140 0.0001 nan 0.0500 0.0000
## 160 0.0001 nan 0.0500 -0.0000
## 180 0.0000 nan 0.0500 -0.0000
## 200 0.0000 nan 0.0500 -0.0000
##
## - Fold21: shrinkage=0.05, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold21: shrinkage=0.05, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0399 nan 0.0500 0.0021
## 2 0.0370 nan 0.0500 0.0030
## 3 0.0349 nan 0.0500 0.0014
## 4 0.0322 nan 0.0500 0.0010
## 5 0.0295 nan 0.0500 0.0025
## 6 0.0272 nan 0.0500 0.0020
## 7 0.0255 nan 0.0500 0.0013
## 8 0.0241 nan 0.0500 0.0014
## 9 0.0231 nan 0.0500 0.0014
## 10 0.0219 nan 0.0500 0.0008
## 20 0.0115 nan 0.0500 0.0003
## 40 0.0041 nan 0.0500 0.0000
## 60 0.0022 nan 0.0500 -0.0001
## 80 0.0012 nan 0.0500 -0.0000
## 100 0.0007 nan 0.0500 -0.0000
## 120 0.0005 nan 0.0500 -0.0000
## 140 0.0003 nan 0.0500 -0.0000
## 160 0.0002 nan 0.0500 -0.0000
## 180 0.0002 nan 0.0500 -0.0000
## 200 0.0001 nan 0.0500 -0.0000
##
## - Fold21: shrinkage=0.05, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold21: shrinkage=0.05, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0392 nan 0.0500 0.0028
## 2 0.0372 nan 0.0500 0.0019
## 3 0.0345 nan 0.0500 0.0022
## 4 0.0320 nan 0.0500 0.0012
## 5 0.0306 nan 0.0500 0.0014
## 6 0.0293 nan 0.0500 0.0007
## 7 0.0272 nan 0.0500 0.0012
## 8 0.0260 nan 0.0500 0.0006
## 9 0.0241 nan 0.0500 0.0012
## 10 0.0230 nan 0.0500 0.0011
## 20 0.0150 nan 0.0500 0.0001
## 40 0.0078 nan 0.0500 0.0001
## 60 0.0046 nan 0.0500 0.0001
## 80 0.0035 nan 0.0500 -0.0000
## 100 0.0026 nan 0.0500 0.0000
## 120 0.0020 nan 0.0500 -0.0000
## 140 0.0015 nan 0.0500 -0.0000
## 160 0.0011 nan 0.0500 0.0000
## 180 0.0008 nan 0.0500 0.0000
## 200 0.0006 nan 0.0500 0.0000
##
## - Fold21: shrinkage=0.05, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold21: shrinkage=0.05, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0387 nan 0.0500 0.0026
## 2 0.0361 nan 0.0500 -0.0001
## 3 0.0340 nan 0.0500 0.0002
## 4 0.0319 nan 0.0500 0.0022
## 5 0.0293 nan 0.0500 0.0024
## 6 0.0271 nan 0.0500 0.0017
## 7 0.0249 nan 0.0500 0.0021
## 8 0.0229 nan 0.0500 0.0009
## 9 0.0215 nan 0.0500 0.0004
## 10 0.0203 nan 0.0500 0.0003
## 20 0.0101 nan 0.0500 0.0004
## 40 0.0028 nan 0.0500 -0.0000
## 60 0.0010 nan 0.0500 -0.0000
## 80 0.0004 nan 0.0500 -0.0000
## 100 0.0002 nan 0.0500 0.0000
## 120 0.0001 nan 0.0500 0.0000
## 140 0.0000 nan 0.0500 -0.0000
## 160 0.0000 nan 0.0500 -0.0000
## 180 0.0000 nan 0.0500 -0.0000
## 200 0.0000 nan 0.0500 -0.0000
##
## - Fold21: shrinkage=0.05, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold21: shrinkage=0.05, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0392 nan 0.0500 0.0022
## 2 0.0364 nan 0.0500 0.0027
## 3 0.0337 nan 0.0500 0.0016
## 4 0.0314 nan 0.0500 0.0016
## 5 0.0299 nan 0.0500 0.0009
## 6 0.0283 nan 0.0500 0.0018
## 7 0.0258 nan 0.0500 0.0016
## 8 0.0242 nan 0.0500 0.0007
## 9 0.0226 nan 0.0500 0.0014
## 10 0.0222 nan 0.0500 -0.0007
## 20 0.0107 nan 0.0500 0.0009
## 40 0.0032 nan 0.0500 -0.0000
## 60 0.0013 nan 0.0500 -0.0000
## 80 0.0007 nan 0.0500 -0.0000
## 100 0.0004 nan 0.0500 -0.0000
## 120 0.0002 nan 0.0500 -0.0000
## 140 0.0002 nan 0.0500 0.0000
## 160 0.0001 nan 0.0500 -0.0000
## 180 0.0001 nan 0.0500 -0.0000
## 200 0.0001 nan 0.0500 0.0000
##
## - Fold21: shrinkage=0.05, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold21: shrinkage=0.05, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0398 nan 0.0500 0.0023
## 2 0.0371 nan 0.0500 0.0026
## 3 0.0344 nan 0.0500 0.0019
## 4 0.0326 nan 0.0500 0.0016
## 5 0.0308 nan 0.0500 0.0020
## 6 0.0291 nan 0.0500 0.0017
## 7 0.0285 nan 0.0500 -0.0006
## 8 0.0273 nan 0.0500 0.0011
## 9 0.0259 nan 0.0500 0.0009
## 10 0.0250 nan 0.0500 0.0008
## 20 0.0161 nan 0.0500 0.0001
## 40 0.0088 nan 0.0500 0.0002
## 60 0.0058 nan 0.0500 0.0001
## 80 0.0038 nan 0.0500 0.0000
## 100 0.0026 nan 0.0500 0.0001
## 120 0.0020 nan 0.0500 0.0000
## 140 0.0015 nan 0.0500 0.0000
## 160 0.0012 nan 0.0500 -0.0000
## 180 0.0009 nan 0.0500 0.0000
## 200 0.0008 nan 0.0500 -0.0000
##
## - Fold21: shrinkage=0.05, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold21: shrinkage=0.10, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0391 nan 0.1000 0.0012
## 2 0.0349 nan 0.1000 0.0028
## 3 0.0307 nan 0.1000 0.0040
## 4 0.0271 nan 0.1000 0.0027
## 5 0.0239 nan 0.1000 0.0021
## 6 0.0214 nan 0.1000 0.0022
## 7 0.0190 nan 0.1000 0.0024
## 8 0.0182 nan 0.1000 -0.0005
## 9 0.0180 nan 0.1000 -0.0007
## 10 0.0176 nan 0.1000 -0.0017
## 20 0.0069 nan 0.1000 0.0003
## 40 0.0023 nan 0.1000 0.0001
## 60 0.0008 nan 0.1000 0.0000
## 80 0.0004 nan 0.1000 -0.0000
## 100 0.0002 nan 0.1000 0.0000
## 120 0.0001 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold21: shrinkage=0.10, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold21: shrinkage=0.10, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0371 nan 0.1000 0.0039
## 2 0.0335 nan 0.1000 0.0005
## 3 0.0303 nan 0.1000 0.0016
## 4 0.0266 nan 0.1000 0.0003
## 5 0.0243 nan 0.1000 -0.0002
## 6 0.0211 nan 0.1000 0.0010
## 7 0.0201 nan 0.1000 0.0006
## 8 0.0197 nan 0.1000 -0.0013
## 9 0.0176 nan 0.1000 0.0018
## 10 0.0154 nan 0.1000 0.0007
## 20 0.0083 nan 0.1000 -0.0007
## 40 0.0034 nan 0.1000 -0.0002
## 60 0.0012 nan 0.1000 0.0000
## 80 0.0006 nan 0.1000 -0.0000
## 100 0.0003 nan 0.1000 -0.0000
## 120 0.0002 nan 0.1000 -0.0000
## 140 0.0001 nan 0.1000 -0.0000
## 160 0.0001 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 0.0000
##
## - Fold21: shrinkage=0.10, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold21: shrinkage=0.10, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0370 nan 0.1000 0.0028
## 2 0.0316 nan 0.1000 0.0046
## 3 0.0282 nan 0.1000 0.0032
## 4 0.0247 nan 0.1000 0.0029
## 5 0.0231 nan 0.1000 0.0003
## 6 0.0203 nan 0.1000 0.0023
## 7 0.0183 nan 0.1000 0.0016
## 8 0.0164 nan 0.1000 0.0017
## 9 0.0155 nan 0.1000 0.0003
## 10 0.0150 nan 0.1000 -0.0003
## 20 0.0081 nan 0.1000 0.0004
## 40 0.0034 nan 0.1000 -0.0002
## 60 0.0019 nan 0.1000 -0.0001
## 80 0.0009 nan 0.1000 -0.0001
## 100 0.0004 nan 0.1000 -0.0000
## 120 0.0002 nan 0.1000 -0.0000
## 140 0.0001 nan 0.1000 -0.0000
## 160 0.0001 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 0.0000
## 200 0.0000 nan 0.1000 0.0000
##
## - Fold21: shrinkage=0.10, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold21: shrinkage=0.10, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0353 nan 0.1000 0.0050
## 2 0.0305 nan 0.1000 0.0040
## 3 0.0267 nan 0.1000 0.0034
## 4 0.0247 nan 0.1000 -0.0011
## 5 0.0209 nan 0.1000 0.0032
## 6 0.0180 nan 0.1000 0.0023
## 7 0.0158 nan 0.1000 0.0016
## 8 0.0143 nan 0.1000 0.0009
## 9 0.0124 nan 0.1000 0.0007
## 10 0.0119 nan 0.1000 0.0004
## 20 0.0052 nan 0.1000 -0.0000
## 40 0.0009 nan 0.1000 0.0000
## 60 0.0002 nan 0.1000 -0.0000
## 80 0.0001 nan 0.1000 -0.0000
## 100 0.0000 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 0.0000
## 200 0.0000 nan 0.1000 0.0000
##
## - Fold21: shrinkage=0.10, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold21: shrinkage=0.10, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0352 nan 0.1000 0.0060
## 2 0.0307 nan 0.1000 0.0047
## 3 0.0267 nan 0.1000 0.0034
## 4 0.0226 nan 0.1000 0.0033
## 5 0.0190 nan 0.1000 0.0026
## 6 0.0157 nan 0.1000 0.0011
## 7 0.0138 nan 0.1000 0.0016
## 8 0.0126 nan 0.1000 0.0007
## 9 0.0117 nan 0.1000 0.0004
## 10 0.0102 nan 0.1000 0.0001
## 20 0.0036 nan 0.1000 -0.0000
## 40 0.0012 nan 0.1000 -0.0000
## 60 0.0005 nan 0.1000 0.0000
## 80 0.0002 nan 0.1000 -0.0000
## 100 0.0001 nan 0.1000 -0.0000
## 120 0.0001 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 0.0000
##
## - Fold21: shrinkage=0.10, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold21: shrinkage=0.10, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0383 nan 0.1000 0.0028
## 2 0.0335 nan 0.1000 0.0045
## 3 0.0299 nan 0.1000 0.0042
## 4 0.0260 nan 0.1000 0.0016
## 5 0.0235 nan 0.1000 0.0022
## 6 0.0202 nan 0.1000 0.0019
## 7 0.0185 nan 0.1000 0.0015
## 8 0.0172 nan 0.1000 -0.0009
## 9 0.0158 nan 0.1000 0.0007
## 10 0.0153 nan 0.1000 -0.0002
## 20 0.0089 nan 0.1000 0.0003
## 40 0.0037 nan 0.1000 0.0000
## 60 0.0020 nan 0.1000 0.0001
## 80 0.0013 nan 0.1000 0.0000
## 100 0.0007 nan 0.1000 -0.0000
## 120 0.0004 nan 0.1000 0.0000
## 140 0.0003 nan 0.1000 -0.0000
## 160 0.0002 nan 0.1000 -0.0000
## 180 0.0001 nan 0.1000 -0.0000
## 200 0.0001 nan 0.1000 -0.0000
##
## - Fold21: shrinkage=0.10, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold21: shrinkage=0.10, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0350 nan 0.1000 0.0052
## 2 0.0298 nan 0.1000 0.0043
## 3 0.0243 nan 0.1000 0.0053
## 4 0.0216 nan 0.1000 0.0012
## 5 0.0194 nan 0.1000 0.0018
## 6 0.0162 nan 0.1000 0.0008
## 7 0.0131 nan 0.1000 0.0024
## 8 0.0120 nan 0.1000 0.0006
## 9 0.0105 nan 0.1000 0.0008
## 10 0.0096 nan 0.1000 0.0009
## 20 0.0040 nan 0.1000 0.0003
## 40 0.0007 nan 0.1000 -0.0000
## 60 0.0002 nan 0.1000 0.0000
## 80 0.0000 nan 0.1000 -0.0000
## 100 0.0000 nan 0.1000 0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 0.0000
##
## - Fold21: shrinkage=0.10, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold21: shrinkage=0.10, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0355 nan 0.1000 0.0036
## 2 0.0314 nan 0.1000 0.0032
## 3 0.0274 nan 0.1000 0.0027
## 4 0.0238 nan 0.1000 0.0036
## 5 0.0226 nan 0.1000 0.0003
## 6 0.0214 nan 0.1000 -0.0010
## 7 0.0181 nan 0.1000 0.0027
## 8 0.0161 nan 0.1000 0.0016
## 9 0.0142 nan 0.1000 0.0017
## 10 0.0130 nan 0.1000 0.0006
## 20 0.0037 nan 0.1000 0.0002
## 40 0.0007 nan 0.1000 0.0000
## 60 0.0002 nan 0.1000 -0.0000
## 80 0.0001 nan 0.1000 -0.0000
## 100 0.0000 nan 0.1000 0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold21: shrinkage=0.10, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold21: shrinkage=0.10, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0371 nan 0.1000 0.0048
## 2 0.0326 nan 0.1000 0.0047
## 3 0.0291 nan 0.1000 0.0041
## 4 0.0273 nan 0.1000 0.0001
## 5 0.0245 nan 0.1000 0.0022
## 6 0.0229 nan 0.1000 0.0003
## 7 0.0205 nan 0.1000 0.0017
## 8 0.0195 nan 0.1000 0.0004
## 9 0.0180 nan 0.1000 0.0012
## 10 0.0166 nan 0.1000 0.0004
## 20 0.0090 nan 0.1000 0.0007
## 40 0.0039 nan 0.1000 0.0000
## 60 0.0016 nan 0.1000 0.0000
## 80 0.0009 nan 0.1000 -0.0000
## 100 0.0006 nan 0.1000 -0.0000
## 120 0.0003 nan 0.1000 -0.0000
## 140 0.0002 nan 0.1000 -0.0000
## 160 0.0002 nan 0.1000 -0.0000
## 180 0.0001 nan 0.1000 -0.0000
## 200 0.0001 nan 0.1000 -0.0000
##
## - Fold21: shrinkage=0.10, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold22: shrinkage=0.01, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0412 nan 0.0100 0.0005
## 2 0.0408 nan 0.0100 0.0004
## 3 0.0402 nan 0.0100 0.0006
## 4 0.0399 nan 0.0100 0.0004
## 5 0.0392 nan 0.0100 0.0005
## 6 0.0387 nan 0.0100 0.0005
## 7 0.0383 nan 0.0100 0.0005
## 8 0.0379 nan 0.0100 0.0005
## 9 0.0374 nan 0.0100 0.0003
## 10 0.0369 nan 0.0100 0.0005
## 20 0.0330 nan 0.0100 0.0004
## 40 0.0273 nan 0.0100 0.0000
## 60 0.0219 nan 0.0100 0.0003
## 80 0.0179 nan 0.0100 0.0002
## 100 0.0149 nan 0.0100 -0.0000
## 120 0.0124 nan 0.0100 0.0001
## 140 0.0102 nan 0.0100 0.0001
## 160 0.0085 nan 0.0100 -0.0000
## 180 0.0074 nan 0.0100 0.0000
## 200 0.0063 nan 0.0100 0.0000
##
## - Fold22: shrinkage=0.01, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold22: shrinkage=0.01, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0411 nan 0.0100 0.0006
## 2 0.0407 nan 0.0100 0.0002
## 3 0.0400 nan 0.0100 0.0006
## 4 0.0394 nan 0.0100 0.0005
## 5 0.0388 nan 0.0100 0.0005
## 6 0.0386 nan 0.0100 -0.0001
## 7 0.0382 nan 0.0100 0.0003
## 8 0.0377 nan 0.0100 0.0005
## 9 0.0372 nan 0.0100 0.0005
## 10 0.0366 nan 0.0100 0.0004
## 20 0.0325 nan 0.0100 0.0004
## 40 0.0258 nan 0.0100 0.0002
## 60 0.0211 nan 0.0100 0.0002
## 80 0.0177 nan 0.0100 0.0001
## 100 0.0144 nan 0.0100 0.0000
## 120 0.0118 nan 0.0100 0.0001
## 140 0.0099 nan 0.0100 0.0000
## 160 0.0084 nan 0.0100 0.0000
## 180 0.0072 nan 0.0100 0.0001
## 200 0.0062 nan 0.0100 -0.0000
##
## - Fold22: shrinkage=0.01, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold22: shrinkage=0.01, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0411 nan 0.0100 0.0006
## 2 0.0407 nan 0.0100 0.0003
## 3 0.0401 nan 0.0100 0.0005
## 4 0.0397 nan 0.0100 0.0005
## 5 0.0391 nan 0.0100 0.0004
## 6 0.0386 nan 0.0100 0.0005
## 7 0.0382 nan 0.0100 0.0004
## 8 0.0377 nan 0.0100 0.0004
## 9 0.0373 nan 0.0100 0.0004
## 10 0.0371 nan 0.0100 -0.0002
## 20 0.0338 nan 0.0100 0.0004
## 40 0.0276 nan 0.0100 0.0003
## 60 0.0225 nan 0.0100 0.0001
## 80 0.0187 nan 0.0100 0.0000
## 100 0.0158 nan 0.0100 0.0000
## 120 0.0135 nan 0.0100 0.0001
## 140 0.0116 nan 0.0100 0.0000
## 160 0.0103 nan 0.0100 0.0001
## 180 0.0092 nan 0.0100 -0.0000
## 200 0.0083 nan 0.0100 0.0000
##
## - Fold22: shrinkage=0.01, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold22: shrinkage=0.01, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0411 nan 0.0100 0.0001
## 2 0.0406 nan 0.0100 0.0004
## 3 0.0400 nan 0.0100 0.0006
## 4 0.0396 nan 0.0100 0.0005
## 5 0.0390 nan 0.0100 0.0006
## 6 0.0384 nan 0.0100 0.0006
## 7 0.0379 nan 0.0100 0.0005
## 8 0.0375 nan 0.0100 -0.0000
## 9 0.0368 nan 0.0100 0.0002
## 10 0.0365 nan 0.0100 0.0001
## 20 0.0318 nan 0.0100 0.0005
## 40 0.0243 nan 0.0100 -0.0000
## 60 0.0184 nan 0.0100 0.0002
## 80 0.0142 nan 0.0100 -0.0000
## 100 0.0111 nan 0.0100 0.0001
## 120 0.0086 nan 0.0100 0.0001
## 140 0.0070 nan 0.0100 0.0001
## 160 0.0057 nan 0.0100 0.0000
## 180 0.0046 nan 0.0100 0.0000
## 200 0.0036 nan 0.0100 0.0000
##
## - Fold22: shrinkage=0.01, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold22: shrinkage=0.01, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0411 nan 0.0100 0.0004
## 2 0.0403 nan 0.0100 0.0005
## 3 0.0398 nan 0.0100 0.0005
## 4 0.0393 nan 0.0100 0.0005
## 5 0.0387 nan 0.0100 0.0005
## 6 0.0384 nan 0.0100 0.0001
## 7 0.0378 nan 0.0100 0.0005
## 8 0.0372 nan 0.0100 0.0006
## 9 0.0367 nan 0.0100 0.0002
## 10 0.0364 nan 0.0100 0.0003
## 20 0.0320 nan 0.0100 0.0005
## 40 0.0244 nan 0.0100 0.0002
## 60 0.0191 nan 0.0100 0.0001
## 80 0.0150 nan 0.0100 0.0000
## 100 0.0121 nan 0.0100 0.0001
## 120 0.0100 nan 0.0100 0.0001
## 140 0.0079 nan 0.0100 0.0001
## 160 0.0065 nan 0.0100 0.0001
## 180 0.0053 nan 0.0100 0.0000
## 200 0.0044 nan 0.0100 0.0000
##
## - Fold22: shrinkage=0.01, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold22: shrinkage=0.01, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0411 nan 0.0100 0.0006
## 2 0.0405 nan 0.0100 0.0006
## 3 0.0400 nan 0.0100 0.0005
## 4 0.0393 nan 0.0100 0.0005
## 5 0.0389 nan 0.0100 0.0002
## 6 0.0384 nan 0.0100 0.0005
## 7 0.0381 nan 0.0100 0.0003
## 8 0.0376 nan 0.0100 0.0004
## 9 0.0370 nan 0.0100 0.0004
## 10 0.0367 nan 0.0100 0.0003
## 20 0.0323 nan 0.0100 0.0004
## 40 0.0257 nan 0.0100 0.0002
## 60 0.0210 nan 0.0100 0.0002
## 80 0.0179 nan 0.0100 0.0000
## 100 0.0152 nan 0.0100 0.0001
## 120 0.0132 nan 0.0100 0.0001
## 140 0.0116 nan 0.0100 0.0001
## 160 0.0102 nan 0.0100 0.0001
## 180 0.0092 nan 0.0100 -0.0000
## 200 0.0084 nan 0.0100 -0.0000
##
## - Fold22: shrinkage=0.01, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold22: shrinkage=0.01, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0411 nan 0.0100 0.0002
## 2 0.0407 nan 0.0100 0.0003
## 3 0.0402 nan 0.0100 -0.0000
## 4 0.0398 nan 0.0100 0.0003
## 5 0.0392 nan 0.0100 0.0004
## 6 0.0385 nan 0.0100 0.0006
## 7 0.0378 nan 0.0100 0.0005
## 8 0.0373 nan 0.0100 0.0006
## 9 0.0366 nan 0.0100 0.0006
## 10 0.0359 nan 0.0100 0.0004
## 20 0.0309 nan 0.0100 0.0004
## 40 0.0228 nan 0.0100 0.0001
## 60 0.0175 nan 0.0100 0.0002
## 80 0.0132 nan 0.0100 0.0001
## 100 0.0099 nan 0.0100 0.0001
## 120 0.0077 nan 0.0100 -0.0000
## 140 0.0060 nan 0.0100 0.0001
## 160 0.0047 nan 0.0100 0.0000
## 180 0.0036 nan 0.0100 -0.0000
## 200 0.0029 nan 0.0100 -0.0000
##
## - Fold22: shrinkage=0.01, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold22: shrinkage=0.01, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0410 nan 0.0100 0.0007
## 2 0.0404 nan 0.0100 0.0003
## 3 0.0398 nan 0.0100 0.0004
## 4 0.0392 nan 0.0100 0.0006
## 5 0.0387 nan 0.0100 0.0002
## 6 0.0383 nan 0.0100 0.0004
## 7 0.0378 nan 0.0100 0.0005
## 8 0.0372 nan 0.0100 0.0005
## 9 0.0367 nan 0.0100 0.0004
## 10 0.0362 nan 0.0100 0.0002
## 20 0.0312 nan 0.0100 0.0000
## 40 0.0238 nan 0.0100 0.0003
## 60 0.0181 nan 0.0100 0.0001
## 80 0.0141 nan 0.0100 0.0001
## 100 0.0110 nan 0.0100 0.0001
## 120 0.0088 nan 0.0100 0.0001
## 140 0.0070 nan 0.0100 0.0001
## 160 0.0057 nan 0.0100 0.0001
## 180 0.0047 nan 0.0100 0.0000
## 200 0.0039 nan 0.0100 -0.0000
##
## - Fold22: shrinkage=0.01, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold22: shrinkage=0.01, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0411 nan 0.0100 0.0003
## 2 0.0405 nan 0.0100 0.0006
## 3 0.0400 nan 0.0100 0.0005
## 4 0.0398 nan 0.0100 0.0000
## 5 0.0394 nan 0.0100 0.0004
## 6 0.0389 nan 0.0100 0.0005
## 7 0.0385 nan 0.0100 0.0002
## 8 0.0380 nan 0.0100 0.0005
## 9 0.0377 nan 0.0100 0.0002
## 10 0.0371 nan 0.0100 0.0005
## 20 0.0330 nan 0.0100 0.0003
## 40 0.0264 nan 0.0100 0.0001
## 60 0.0220 nan 0.0100 0.0002
## 80 0.0181 nan 0.0100 0.0001
## 100 0.0154 nan 0.0100 0.0001
## 120 0.0132 nan 0.0100 -0.0000
## 140 0.0118 nan 0.0100 -0.0000
## 160 0.0103 nan 0.0100 -0.0000
## 180 0.0090 nan 0.0100 0.0001
## 200 0.0080 nan 0.0100 0.0000
##
## - Fold22: shrinkage=0.01, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold22: shrinkage=0.05, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0383 nan 0.0500 0.0020
## 2 0.0378 nan 0.0500 -0.0011
## 3 0.0366 nan 0.0500 0.0004
## 4 0.0340 nan 0.0500 0.0020
## 5 0.0322 nan 0.0500 0.0009
## 6 0.0300 nan 0.0500 0.0015
## 7 0.0279 nan 0.0500 0.0019
## 8 0.0260 nan 0.0500 0.0014
## 9 0.0243 nan 0.0500 0.0016
## 10 0.0235 nan 0.0500 -0.0001
## 20 0.0145 nan 0.0500 0.0005
## 40 0.0066 nan 0.0500 0.0002
## 60 0.0033 nan 0.0500 0.0002
## 80 0.0020 nan 0.0500 0.0000
## 100 0.0012 nan 0.0500 -0.0000
## 120 0.0007 nan 0.0500 0.0000
## 140 0.0005 nan 0.0500 -0.0000
## 160 0.0003 nan 0.0500 -0.0000
## 180 0.0002 nan 0.0500 -0.0000
## 200 0.0001 nan 0.0500 -0.0000
##
## - Fold22: shrinkage=0.05, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold22: shrinkage=0.05, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0396 nan 0.0500 0.0016
## 2 0.0363 nan 0.0500 0.0017
## 3 0.0343 nan 0.0500 0.0018
## 4 0.0323 nan 0.0500 0.0020
## 5 0.0315 nan 0.0500 -0.0003
## 6 0.0308 nan 0.0500 -0.0007
## 7 0.0291 nan 0.0500 0.0008
## 8 0.0277 nan 0.0500 0.0008
## 9 0.0265 nan 0.0500 0.0001
## 10 0.0249 nan 0.0500 0.0015
## 20 0.0148 nan 0.0500 0.0005
## 40 0.0062 nan 0.0500 0.0000
## 60 0.0032 nan 0.0500 0.0001
## 80 0.0019 nan 0.0500 0.0000
## 100 0.0011 nan 0.0500 0.0000
## 120 0.0007 nan 0.0500 0.0000
## 140 0.0005 nan 0.0500 -0.0000
## 160 0.0003 nan 0.0500 -0.0000
## 180 0.0002 nan 0.0500 -0.0000
## 200 0.0001 nan 0.0500 -0.0000
##
## - Fold22: shrinkage=0.05, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold22: shrinkage=0.05, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0388 nan 0.0500 0.0024
## 2 0.0363 nan 0.0500 0.0024
## 3 0.0344 nan 0.0500 0.0015
## 4 0.0325 nan 0.0500 0.0019
## 5 0.0317 nan 0.0500 0.0010
## 6 0.0297 nan 0.0500 0.0010
## 7 0.0283 nan 0.0500 0.0012
## 8 0.0261 nan 0.0500 0.0009
## 9 0.0247 nan 0.0500 0.0014
## 10 0.0234 nan 0.0500 0.0006
## 20 0.0149 nan 0.0500 0.0003
## 40 0.0082 nan 0.0500 0.0002
## 60 0.0054 nan 0.0500 -0.0000
## 80 0.0036 nan 0.0500 -0.0000
## 100 0.0022 nan 0.0500 -0.0000
## 120 0.0015 nan 0.0500 0.0000
## 140 0.0010 nan 0.0500 -0.0000
## 160 0.0007 nan 0.0500 -0.0000
## 180 0.0005 nan 0.0500 0.0000
## 200 0.0004 nan 0.0500 -0.0000
##
## - Fold22: shrinkage=0.05, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold22: shrinkage=0.05, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0394 nan 0.0500 0.0018
## 2 0.0369 nan 0.0500 0.0018
## 3 0.0348 nan 0.0500 0.0016
## 4 0.0333 nan 0.0500 0.0002
## 5 0.0311 nan 0.0500 0.0023
## 6 0.0285 nan 0.0500 0.0023
## 7 0.0273 nan 0.0500 0.0012
## 8 0.0255 nan 0.0500 0.0012
## 9 0.0243 nan 0.0500 0.0012
## 10 0.0223 nan 0.0500 0.0005
## 20 0.0113 nan 0.0500 0.0002
## 40 0.0040 nan 0.0500 -0.0001
## 60 0.0016 nan 0.0500 0.0000
## 80 0.0008 nan 0.0500 -0.0000
## 100 0.0004 nan 0.0500 0.0000
## 120 0.0002 nan 0.0500 -0.0000
## 140 0.0001 nan 0.0500 0.0000
## 160 0.0000 nan 0.0500 -0.0000
## 180 0.0000 nan 0.0500 -0.0000
## 200 0.0000 nan 0.0500 -0.0000
##
## - Fold22: shrinkage=0.05, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold22: shrinkage=0.05, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0378 nan 0.0500 0.0016
## 2 0.0359 nan 0.0500 0.0012
## 3 0.0336 nan 0.0500 0.0017
## 4 0.0313 nan 0.0500 0.0015
## 5 0.0295 nan 0.0500 0.0018
## 6 0.0276 nan 0.0500 0.0017
## 7 0.0262 nan 0.0500 0.0008
## 8 0.0247 nan 0.0500 0.0009
## 9 0.0232 nan 0.0500 0.0015
## 10 0.0219 nan 0.0500 0.0011
## 20 0.0125 nan 0.0500 0.0007
## 40 0.0045 nan 0.0500 0.0003
## 60 0.0023 nan 0.0500 -0.0001
## 80 0.0012 nan 0.0500 0.0000
## 100 0.0006 nan 0.0500 -0.0000
## 120 0.0003 nan 0.0500 -0.0000
## 140 0.0002 nan 0.0500 0.0000
## 160 0.0001 nan 0.0500 -0.0000
## 180 0.0001 nan 0.0500 -0.0000
## 200 0.0001 nan 0.0500 0.0000
##
## - Fold22: shrinkage=0.05, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold22: shrinkage=0.05, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0388 nan 0.0500 0.0029
## 2 0.0375 nan 0.0500 0.0013
## 3 0.0348 nan 0.0500 0.0015
## 4 0.0329 nan 0.0500 0.0021
## 5 0.0320 nan 0.0500 0.0006
## 6 0.0300 nan 0.0500 0.0021
## 7 0.0280 nan 0.0500 0.0017
## 8 0.0263 nan 0.0500 0.0014
## 9 0.0251 nan 0.0500 0.0014
## 10 0.0235 nan 0.0500 0.0014
## 20 0.0146 nan 0.0500 0.0001
## 40 0.0072 nan 0.0500 0.0002
## 60 0.0042 nan 0.0500 0.0000
## 80 0.0028 nan 0.0500 0.0001
## 100 0.0017 nan 0.0500 -0.0000
## 120 0.0013 nan 0.0500 -0.0000
## 140 0.0009 nan 0.0500 0.0000
## 160 0.0006 nan 0.0500 0.0000
## 180 0.0004 nan 0.0500 -0.0000
## 200 0.0003 nan 0.0500 -0.0000
##
## - Fold22: shrinkage=0.05, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold22: shrinkage=0.05, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0384 nan 0.0500 0.0033
## 2 0.0355 nan 0.0500 0.0030
## 3 0.0334 nan 0.0500 0.0015
## 4 0.0303 nan 0.0500 0.0014
## 5 0.0281 nan 0.0500 0.0014
## 6 0.0264 nan 0.0500 0.0011
## 7 0.0245 nan 0.0500 0.0008
## 8 0.0239 nan 0.0500 -0.0004
## 9 0.0232 nan 0.0500 -0.0012
## 10 0.0215 nan 0.0500 0.0015
## 20 0.0114 nan 0.0500 0.0010
## 40 0.0038 nan 0.0500 0.0002
## 60 0.0011 nan 0.0500 0.0000
## 80 0.0004 nan 0.0500 0.0000
## 100 0.0002 nan 0.0500 0.0000
## 120 0.0001 nan 0.0500 -0.0000
## 140 0.0000 nan 0.0500 -0.0000
## 160 0.0000 nan 0.0500 0.0000
## 180 0.0000 nan 0.0500 -0.0000
## 200 0.0000 nan 0.0500 0.0000
##
## - Fold22: shrinkage=0.05, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold22: shrinkage=0.05, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0401 nan 0.0500 0.0008
## 2 0.0384 nan 0.0500 0.0010
## 3 0.0357 nan 0.0500 0.0020
## 4 0.0335 nan 0.0500 0.0023
## 5 0.0309 nan 0.0500 0.0024
## 6 0.0288 nan 0.0500 0.0021
## 7 0.0268 nan 0.0500 0.0018
## 8 0.0252 nan 0.0500 0.0003
## 9 0.0229 nan 0.0500 0.0013
## 10 0.0212 nan 0.0500 0.0017
## 20 0.0122 nan 0.0500 0.0007
## 40 0.0048 nan 0.0500 -0.0000
## 60 0.0020 nan 0.0500 -0.0000
## 80 0.0011 nan 0.0500 0.0000
## 100 0.0006 nan 0.0500 -0.0000
## 120 0.0003 nan 0.0500 -0.0000
## 140 0.0002 nan 0.0500 0.0000
## 160 0.0001 nan 0.0500 0.0000
## 180 0.0001 nan 0.0500 -0.0000
## 200 0.0001 nan 0.0500 0.0000
##
## - Fold22: shrinkage=0.05, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold22: shrinkage=0.05, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0384 nan 0.0500 0.0026
## 2 0.0360 nan 0.0500 0.0025
## 3 0.0336 nan 0.0500 0.0024
## 4 0.0326 nan 0.0500 -0.0000
## 5 0.0307 nan 0.0500 0.0018
## 6 0.0300 nan 0.0500 -0.0004
## 7 0.0281 nan 0.0500 0.0001
## 8 0.0266 nan 0.0500 0.0007
## 9 0.0261 nan 0.0500 -0.0001
## 10 0.0251 nan 0.0500 0.0010
## 20 0.0154 nan 0.0500 0.0006
## 40 0.0085 nan 0.0500 -0.0002
## 60 0.0053 nan 0.0500 0.0000
## 80 0.0037 nan 0.0500 0.0000
## 100 0.0024 nan 0.0500 0.0000
## 120 0.0017 nan 0.0500 0.0000
## 140 0.0012 nan 0.0500 0.0000
## 160 0.0009 nan 0.0500 -0.0000
## 180 0.0007 nan 0.0500 -0.0000
## 200 0.0006 nan 0.0500 0.0000
##
## - Fold22: shrinkage=0.05, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold22: shrinkage=0.10, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0366 nan 0.1000 0.0049
## 2 0.0330 nan 0.1000 0.0043
## 3 0.0295 nan 0.1000 0.0015
## 4 0.0270 nan 0.1000 0.0021
## 5 0.0244 nan 0.1000 0.0026
## 6 0.0219 nan 0.1000 0.0020
## 7 0.0200 nan 0.1000 0.0013
## 8 0.0191 nan 0.1000 0.0003
## 9 0.0177 nan 0.1000 0.0013
## 10 0.0167 nan 0.1000 0.0006
## 20 0.0064 nan 0.1000 0.0001
## 40 0.0018 nan 0.1000 -0.0001
## 60 0.0007 nan 0.1000 -0.0000
## 80 0.0003 nan 0.1000 -0.0000
## 100 0.0001 nan 0.1000 -0.0000
## 120 0.0001 nan 0.1000 0.0000
## 140 0.0000 nan 0.1000 0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold22: shrinkage=0.10, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold22: shrinkage=0.10, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0359 nan 0.1000 0.0051
## 2 0.0316 nan 0.1000 0.0041
## 3 0.0294 nan 0.1000 -0.0000
## 4 0.0256 nan 0.1000 0.0031
## 5 0.0223 nan 0.1000 0.0029
## 6 0.0197 nan 0.1000 0.0021
## 7 0.0178 nan 0.1000 -0.0001
## 8 0.0171 nan 0.1000 0.0001
## 9 0.0155 nan 0.1000 0.0015
## 10 0.0147 nan 0.1000 -0.0004
## 20 0.0061 nan 0.1000 0.0002
## 40 0.0016 nan 0.1000 0.0000
## 60 0.0007 nan 0.1000 -0.0000
## 80 0.0002 nan 0.1000 -0.0000
## 100 0.0001 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 0.0000
## 200 0.0000 nan 0.1000 0.0000
##
## - Fold22: shrinkage=0.10, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold22: shrinkage=0.10, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0358 nan 0.1000 0.0033
## 2 0.0317 nan 0.1000 0.0043
## 3 0.0285 nan 0.1000 0.0012
## 4 0.0267 nan 0.1000 0.0014
## 5 0.0241 nan 0.1000 0.0005
## 6 0.0219 nan 0.1000 0.0021
## 7 0.0201 nan 0.1000 0.0018
## 8 0.0185 nan 0.1000 0.0008
## 9 0.0171 nan 0.1000 0.0007
## 10 0.0158 nan 0.1000 0.0013
## 20 0.0072 nan 0.1000 0.0001
## 40 0.0026 nan 0.1000 0.0000
## 60 0.0013 nan 0.1000 0.0000
## 80 0.0007 nan 0.1000 -0.0000
## 100 0.0004 nan 0.1000 -0.0000
## 120 0.0002 nan 0.1000 0.0000
## 140 0.0001 nan 0.1000 -0.0000
## 160 0.0001 nan 0.1000 -0.0000
## 180 0.0001 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold22: shrinkage=0.10, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold22: shrinkage=0.10, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0363 nan 0.1000 0.0033
## 2 0.0329 nan 0.1000 0.0028
## 3 0.0263 nan 0.1000 0.0069
## 4 0.0223 nan 0.1000 0.0018
## 5 0.0188 nan 0.1000 0.0023
## 6 0.0166 nan 0.1000 0.0018
## 7 0.0146 nan 0.1000 0.0011
## 8 0.0125 nan 0.1000 0.0021
## 9 0.0108 nan 0.1000 0.0013
## 10 0.0096 nan 0.1000 0.0008
## 20 0.0029 nan 0.1000 0.0003
## 40 0.0005 nan 0.1000 0.0000
## 60 0.0001 nan 0.1000 -0.0000
## 80 0.0000 nan 0.1000 -0.0000
## 100 0.0000 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold22: shrinkage=0.10, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold22: shrinkage=0.10, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0358 nan 0.1000 0.0052
## 2 0.0305 nan 0.1000 0.0048
## 3 0.0266 nan 0.1000 0.0022
## 4 0.0239 nan 0.1000 0.0017
## 5 0.0208 nan 0.1000 0.0030
## 6 0.0192 nan 0.1000 -0.0001
## 7 0.0167 nan 0.1000 0.0027
## 8 0.0159 nan 0.1000 -0.0001
## 9 0.0135 nan 0.1000 0.0005
## 10 0.0119 nan 0.1000 0.0007
## 20 0.0047 nan 0.1000 0.0000
## 40 0.0010 nan 0.1000 -0.0000
## 60 0.0004 nan 0.1000 -0.0000
## 80 0.0002 nan 0.1000 -0.0000
## 100 0.0001 nan 0.1000 -0.0000
## 120 0.0001 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 0.0000
##
## - Fold22: shrinkage=0.10, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold22: shrinkage=0.10, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0369 nan 0.1000 0.0052
## 2 0.0323 nan 0.1000 0.0041
## 3 0.0295 nan 0.1000 0.0023
## 4 0.0266 nan 0.1000 -0.0003
## 5 0.0236 nan 0.1000 0.0025
## 6 0.0214 nan 0.1000 0.0013
## 7 0.0186 nan 0.1000 0.0011
## 8 0.0178 nan 0.1000 0.0005
## 9 0.0157 nan 0.1000 0.0013
## 10 0.0145 nan 0.1000 0.0002
## 20 0.0080 nan 0.1000 -0.0002
## 40 0.0029 nan 0.1000 -0.0000
## 60 0.0013 nan 0.1000 -0.0001
## 80 0.0006 nan 0.1000 0.0000
## 100 0.0003 nan 0.1000 -0.0000
## 120 0.0002 nan 0.1000 0.0000
## 140 0.0001 nan 0.1000 -0.0000
## 160 0.0001 nan 0.1000 -0.0000
## 180 0.0001 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold22: shrinkage=0.10, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold22: shrinkage=0.10, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0375 nan 0.1000 0.0009
## 2 0.0340 nan 0.1000 -0.0003
## 3 0.0283 nan 0.1000 0.0046
## 4 0.0242 nan 0.1000 0.0033
## 5 0.0201 nan 0.1000 0.0022
## 6 0.0177 nan 0.1000 0.0028
## 7 0.0153 nan 0.1000 0.0014
## 8 0.0126 nan 0.1000 0.0026
## 9 0.0116 nan 0.1000 0.0001
## 10 0.0095 nan 0.1000 0.0013
## 20 0.0028 nan 0.1000 -0.0001
## 40 0.0004 nan 0.1000 -0.0000
## 60 0.0001 nan 0.1000 0.0000
## 80 0.0000 nan 0.1000 0.0000
## 100 0.0000 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 0.0000
## 200 0.0000 nan 0.1000 0.0000
##
## - Fold22: shrinkage=0.10, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold22: shrinkage=0.10, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0369 nan 0.1000 0.0013
## 2 0.0318 nan 0.1000 0.0021
## 3 0.0274 nan 0.1000 0.0034
## 4 0.0247 nan 0.1000 0.0033
## 5 0.0222 nan 0.1000 0.0015
## 6 0.0189 nan 0.1000 0.0033
## 7 0.0158 nan 0.1000 0.0022
## 8 0.0140 nan 0.1000 0.0009
## 9 0.0115 nan 0.1000 0.0014
## 10 0.0105 nan 0.1000 0.0004
## 20 0.0039 nan 0.1000 0.0001
## 40 0.0012 nan 0.1000 -0.0000
## 60 0.0004 nan 0.1000 0.0000
## 80 0.0002 nan 0.1000 -0.0000
## 100 0.0001 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold22: shrinkage=0.10, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold22: shrinkage=0.10, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0354 nan 0.1000 0.0048
## 2 0.0316 nan 0.1000 0.0042
## 3 0.0272 nan 0.1000 0.0024
## 4 0.0245 nan 0.1000 0.0014
## 5 0.0226 nan 0.1000 0.0012
## 6 0.0222 nan 0.1000 -0.0011
## 7 0.0200 nan 0.1000 0.0018
## 8 0.0185 nan 0.1000 0.0014
## 9 0.0171 nan 0.1000 0.0009
## 10 0.0155 nan 0.1000 0.0018
## 20 0.0079 nan 0.1000 0.0001
## 40 0.0030 nan 0.1000 0.0002
## 60 0.0013 nan 0.1000 -0.0000
## 80 0.0006 nan 0.1000 -0.0000
## 100 0.0003 nan 0.1000 -0.0000
## 120 0.0002 nan 0.1000 0.0000
## 140 0.0001 nan 0.1000 -0.0000
## 160 0.0001 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold22: shrinkage=0.10, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold23: shrinkage=0.01, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0434 nan 0.0100 0.0006
## 2 0.0428 nan 0.0100 0.0006
## 3 0.0422 nan 0.0100 0.0006
## 4 0.0416 nan 0.0100 0.0003
## 5 0.0411 nan 0.0100 0.0004
## 6 0.0405 nan 0.0100 0.0006
## 7 0.0399 nan 0.0100 0.0005
## 8 0.0393 nan 0.0100 0.0005
## 9 0.0387 nan 0.0100 0.0006
## 10 0.0381 nan 0.0100 0.0003
## 20 0.0339 nan 0.0100 0.0004
## 40 0.0274 nan 0.0100 -0.0000
## 60 0.0219 nan 0.0100 0.0001
## 80 0.0178 nan 0.0100 0.0002
## 100 0.0146 nan 0.0100 0.0001
## 120 0.0122 nan 0.0100 0.0000
## 140 0.0101 nan 0.0100 0.0001
## 160 0.0087 nan 0.0100 0.0001
## 180 0.0071 nan 0.0100 0.0001
## 200 0.0060 nan 0.0100 0.0000
##
## - Fold23: shrinkage=0.01, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold23: shrinkage=0.01, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0435 nan 0.0100 0.0004
## 2 0.0434 nan 0.0100 -0.0002
## 3 0.0429 nan 0.0100 0.0004
## 4 0.0424 nan 0.0100 0.0005
## 5 0.0420 nan 0.0100 0.0003
## 6 0.0415 nan 0.0100 0.0006
## 7 0.0410 nan 0.0100 0.0004
## 8 0.0407 nan 0.0100 0.0003
## 9 0.0403 nan 0.0100 0.0004
## 10 0.0398 nan 0.0100 0.0005
## 20 0.0352 nan 0.0100 0.0002
## 40 0.0279 nan 0.0100 0.0004
## 60 0.0229 nan 0.0100 0.0001
## 80 0.0187 nan 0.0100 0.0001
## 100 0.0154 nan 0.0100 0.0001
## 120 0.0127 nan 0.0100 0.0001
## 140 0.0105 nan 0.0100 0.0000
## 160 0.0088 nan 0.0100 0.0000
## 180 0.0075 nan 0.0100 0.0000
## 200 0.0063 nan 0.0100 0.0000
##
## - Fold23: shrinkage=0.01, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold23: shrinkage=0.01, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0436 nan 0.0100 0.0000
## 2 0.0430 nan 0.0100 0.0004
## 3 0.0424 nan 0.0100 0.0006
## 4 0.0419 nan 0.0100 0.0005
## 5 0.0413 nan 0.0100 0.0003
## 6 0.0409 nan 0.0100 0.0002
## 7 0.0404 nan 0.0100 0.0005
## 8 0.0398 nan 0.0100 0.0005
## 9 0.0392 nan 0.0100 0.0004
## 10 0.0387 nan 0.0100 0.0004
## 20 0.0343 nan 0.0100 0.0004
## 40 0.0270 nan 0.0100 0.0003
## 60 0.0219 nan 0.0100 0.0001
## 80 0.0183 nan 0.0100 0.0002
## 100 0.0156 nan 0.0100 0.0000
## 120 0.0133 nan 0.0100 0.0001
## 140 0.0117 nan 0.0100 0.0000
## 160 0.0099 nan 0.0100 0.0001
## 180 0.0090 nan 0.0100 0.0001
## 200 0.0079 nan 0.0100 -0.0000
##
## - Fold23: shrinkage=0.01, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold23: shrinkage=0.01, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0435 nan 0.0100 0.0006
## 2 0.0429 nan 0.0100 0.0005
## 3 0.0423 nan 0.0100 0.0002
## 4 0.0419 nan 0.0100 0.0001
## 5 0.0413 nan 0.0100 0.0004
## 6 0.0408 nan 0.0100 0.0001
## 7 0.0402 nan 0.0100 0.0005
## 8 0.0394 nan 0.0100 0.0007
## 9 0.0387 nan 0.0100 0.0007
## 10 0.0381 nan 0.0100 0.0006
## 20 0.0333 nan 0.0100 0.0004
## 40 0.0250 nan 0.0100 0.0003
## 60 0.0192 nan 0.0100 0.0002
## 80 0.0151 nan 0.0100 -0.0000
## 100 0.0118 nan 0.0100 0.0000
## 120 0.0093 nan 0.0100 0.0001
## 140 0.0075 nan 0.0100 -0.0001
## 160 0.0061 nan 0.0100 0.0000
## 180 0.0048 nan 0.0100 0.0000
## 200 0.0040 nan 0.0100 0.0000
##
## - Fold23: shrinkage=0.01, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold23: shrinkage=0.01, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0435 nan 0.0100 0.0001
## 2 0.0430 nan 0.0100 0.0006
## 3 0.0424 nan 0.0100 0.0004
## 4 0.0417 nan 0.0100 0.0006
## 5 0.0413 nan 0.0100 0.0003
## 6 0.0409 nan 0.0100 0.0005
## 7 0.0402 nan 0.0100 0.0007
## 8 0.0396 nan 0.0100 0.0006
## 9 0.0392 nan 0.0100 0.0001
## 10 0.0389 nan 0.0100 0.0003
## 20 0.0345 nan 0.0100 0.0004
## 40 0.0267 nan 0.0100 0.0003
## 60 0.0206 nan 0.0100 0.0003
## 80 0.0163 nan 0.0100 0.0002
## 100 0.0129 nan 0.0100 -0.0000
## 120 0.0105 nan 0.0100 0.0000
## 140 0.0083 nan 0.0100 0.0000
## 160 0.0069 nan 0.0100 0.0000
## 180 0.0055 nan 0.0100 0.0001
## 200 0.0044 nan 0.0100 0.0000
##
## - Fold23: shrinkage=0.01, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold23: shrinkage=0.01, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0436 nan 0.0100 0.0003
## 2 0.0435 nan 0.0100 -0.0002
## 3 0.0430 nan 0.0100 0.0006
## 4 0.0424 nan 0.0100 0.0006
## 5 0.0421 nan 0.0100 -0.0002
## 6 0.0415 nan 0.0100 0.0006
## 7 0.0411 nan 0.0100 0.0003
## 8 0.0407 nan 0.0100 0.0003
## 9 0.0405 nan 0.0100 -0.0000
## 10 0.0401 nan 0.0100 0.0003
## 20 0.0355 nan 0.0100 0.0003
## 40 0.0282 nan 0.0100 0.0003
## 60 0.0233 nan 0.0100 0.0002
## 80 0.0194 nan 0.0100 0.0000
## 100 0.0162 nan 0.0100 0.0000
## 120 0.0138 nan 0.0100 0.0000
## 140 0.0121 nan 0.0100 0.0000
## 160 0.0103 nan 0.0100 0.0000
## 180 0.0089 nan 0.0100 0.0000
## 200 0.0081 nan 0.0100 0.0001
##
## - Fold23: shrinkage=0.01, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold23: shrinkage=0.01, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0432 nan 0.0100 0.0006
## 2 0.0425 nan 0.0100 0.0007
## 3 0.0419 nan 0.0100 0.0006
## 4 0.0413 nan 0.0100 0.0007
## 5 0.0406 nan 0.0100 0.0007
## 6 0.0400 nan 0.0100 0.0006
## 7 0.0397 nan 0.0100 0.0002
## 8 0.0390 nan 0.0100 0.0008
## 9 0.0386 nan 0.0100 0.0003
## 10 0.0380 nan 0.0100 0.0003
## 20 0.0333 nan 0.0100 0.0001
## 40 0.0250 nan 0.0100 0.0002
## 60 0.0187 nan 0.0100 0.0002
## 80 0.0143 nan 0.0100 0.0000
## 100 0.0111 nan 0.0100 0.0001
## 120 0.0088 nan 0.0100 0.0001
## 140 0.0070 nan 0.0100 0.0001
## 160 0.0054 nan 0.0100 0.0000
## 180 0.0044 nan 0.0100 0.0000
## 200 0.0034 nan 0.0100 0.0000
##
## - Fold23: shrinkage=0.01, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold23: shrinkage=0.01, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0436 nan 0.0100 0.0003
## 2 0.0431 nan 0.0100 0.0005
## 3 0.0428 nan 0.0100 0.0001
## 4 0.0421 nan 0.0100 0.0004
## 5 0.0419 nan 0.0100 -0.0001
## 6 0.0412 nan 0.0100 0.0003
## 7 0.0406 nan 0.0100 0.0005
## 8 0.0402 nan 0.0100 0.0001
## 9 0.0396 nan 0.0100 0.0005
## 10 0.0390 nan 0.0100 0.0002
## 20 0.0340 nan 0.0100 0.0003
## 40 0.0254 nan 0.0100 0.0002
## 60 0.0199 nan 0.0100 0.0003
## 80 0.0154 nan 0.0100 0.0001
## 100 0.0118 nan 0.0100 0.0001
## 120 0.0098 nan 0.0100 0.0001
## 140 0.0078 nan 0.0100 0.0001
## 160 0.0064 nan 0.0100 0.0001
## 180 0.0051 nan 0.0100 0.0001
## 200 0.0042 nan 0.0100 0.0000
##
## - Fold23: shrinkage=0.01, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold23: shrinkage=0.01, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0436 nan 0.0100 0.0005
## 2 0.0432 nan 0.0100 0.0002
## 3 0.0428 nan 0.0100 0.0003
## 4 0.0422 nan 0.0100 0.0004
## 5 0.0419 nan 0.0100 0.0000
## 6 0.0414 nan 0.0100 0.0003
## 7 0.0410 nan 0.0100 0.0003
## 8 0.0406 nan 0.0100 0.0003
## 9 0.0400 nan 0.0100 0.0006
## 10 0.0395 nan 0.0100 0.0006
## 20 0.0356 nan 0.0100 0.0003
## 40 0.0285 nan 0.0100 0.0001
## 60 0.0235 nan 0.0100 0.0003
## 80 0.0195 nan 0.0100 0.0001
## 100 0.0162 nan 0.0100 0.0001
## 120 0.0139 nan 0.0100 0.0001
## 140 0.0118 nan 0.0100 -0.0000
## 160 0.0102 nan 0.0100 0.0001
## 180 0.0090 nan 0.0100 -0.0000
## 200 0.0079 nan 0.0100 0.0000
##
## - Fold23: shrinkage=0.01, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold23: shrinkage=0.05, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0416 nan 0.0500 0.0011
## 2 0.0400 nan 0.0500 0.0006
## 3 0.0386 nan 0.0500 0.0000
## 4 0.0361 nan 0.0500 0.0017
## 5 0.0350 nan 0.0500 0.0000
## 6 0.0324 nan 0.0500 0.0018
## 7 0.0304 nan 0.0500 0.0022
## 8 0.0290 nan 0.0500 0.0001
## 9 0.0274 nan 0.0500 0.0010
## 10 0.0254 nan 0.0500 0.0017
## 20 0.0142 nan 0.0500 0.0006
## 40 0.0056 nan 0.0500 0.0002
## 60 0.0026 nan 0.0500 0.0000
## 80 0.0013 nan 0.0500 0.0000
## 100 0.0008 nan 0.0500 0.0000
## 120 0.0004 nan 0.0500 -0.0000
## 140 0.0003 nan 0.0500 0.0000
## 160 0.0002 nan 0.0500 0.0000
## 180 0.0001 nan 0.0500 0.0000
## 200 0.0001 nan 0.0500 0.0000
##
## - Fold23: shrinkage=0.05, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold23: shrinkage=0.05, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0411 nan 0.0500 0.0030
## 2 0.0390 nan 0.0500 0.0019
## 3 0.0361 nan 0.0500 0.0031
## 4 0.0335 nan 0.0500 0.0022
## 5 0.0316 nan 0.0500 0.0020
## 6 0.0303 nan 0.0500 0.0008
## 7 0.0286 nan 0.0500 0.0019
## 8 0.0277 nan 0.0500 0.0005
## 9 0.0261 nan 0.0500 0.0014
## 10 0.0252 nan 0.0500 0.0005
## 20 0.0143 nan 0.0500 0.0007
## 40 0.0059 nan 0.0500 0.0001
## 60 0.0028 nan 0.0500 0.0000
## 80 0.0016 nan 0.0500 0.0000
## 100 0.0010 nan 0.0500 0.0000
## 120 0.0006 nan 0.0500 0.0000
## 140 0.0003 nan 0.0500 0.0000
## 160 0.0002 nan 0.0500 -0.0000
## 180 0.0001 nan 0.0500 -0.0000
## 200 0.0001 nan 0.0500 -0.0000
##
## - Fold23: shrinkage=0.05, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold23: shrinkage=0.05, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0409 nan 0.0500 0.0028
## 2 0.0384 nan 0.0500 0.0028
## 3 0.0358 nan 0.0500 0.0024
## 4 0.0350 nan 0.0500 -0.0006
## 5 0.0323 nan 0.0500 0.0021
## 6 0.0302 nan 0.0500 0.0019
## 7 0.0292 nan 0.0500 0.0011
## 8 0.0278 nan 0.0500 0.0016
## 9 0.0272 nan 0.0500 0.0006
## 10 0.0257 nan 0.0500 0.0006
## 20 0.0159 nan 0.0500 0.0003
## 40 0.0083 nan 0.0500 0.0001
## 60 0.0049 nan 0.0500 -0.0001
## 80 0.0035 nan 0.0500 0.0000
## 100 0.0025 nan 0.0500 0.0000
## 120 0.0020 nan 0.0500 -0.0000
## 140 0.0015 nan 0.0500 -0.0000
## 160 0.0010 nan 0.0500 -0.0000
## 180 0.0007 nan 0.0500 -0.0000
## 200 0.0006 nan 0.0500 -0.0000
##
## - Fold23: shrinkage=0.05, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold23: shrinkage=0.05, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0403 nan 0.0500 0.0032
## 2 0.0375 nan 0.0500 0.0018
## 3 0.0346 nan 0.0500 0.0016
## 4 0.0315 nan 0.0500 0.0032
## 5 0.0285 nan 0.0500 0.0014
## 6 0.0266 nan 0.0500 0.0011
## 7 0.0252 nan 0.0500 0.0002
## 8 0.0229 nan 0.0500 0.0016
## 9 0.0222 nan 0.0500 -0.0001
## 10 0.0218 nan 0.0500 -0.0003
## 20 0.0121 nan 0.0500 0.0006
## 40 0.0042 nan 0.0500 0.0001
## 60 0.0014 nan 0.0500 0.0000
## 80 0.0006 nan 0.0500 -0.0000
## 100 0.0003 nan 0.0500 -0.0000
## 120 0.0001 nan 0.0500 0.0000
## 140 0.0001 nan 0.0500 -0.0000
## 160 0.0000 nan 0.0500 -0.0000
## 180 0.0000 nan 0.0500 -0.0000
## 200 0.0000 nan 0.0500 -0.0000
##
## - Fold23: shrinkage=0.05, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold23: shrinkage=0.05, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0417 nan 0.0500 0.0025
## 2 0.0394 nan 0.0500 0.0009
## 3 0.0359 nan 0.0500 0.0032
## 4 0.0332 nan 0.0500 0.0012
## 5 0.0307 nan 0.0500 0.0022
## 6 0.0282 nan 0.0500 0.0018
## 7 0.0263 nan 0.0500 0.0014
## 8 0.0244 nan 0.0500 0.0016
## 9 0.0227 nan 0.0500 0.0018
## 10 0.0208 nan 0.0500 0.0016
## 20 0.0114 nan 0.0500 -0.0001
## 40 0.0037 nan 0.0500 0.0001
## 60 0.0015 nan 0.0500 -0.0000
## 80 0.0009 nan 0.0500 -0.0000
## 100 0.0006 nan 0.0500 -0.0000
## 120 0.0003 nan 0.0500 0.0000
## 140 0.0002 nan 0.0500 0.0000
## 160 0.0001 nan 0.0500 -0.0000
## 180 0.0001 nan 0.0500 0.0000
## 200 0.0001 nan 0.0500 -0.0000
##
## - Fold23: shrinkage=0.05, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold23: shrinkage=0.05, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0415 nan 0.0500 0.0026
## 2 0.0392 nan 0.0500 -0.0005
## 3 0.0363 nan 0.0500 0.0019
## 4 0.0341 nan 0.0500 0.0024
## 5 0.0328 nan 0.0500 -0.0001
## 6 0.0316 nan 0.0500 0.0009
## 7 0.0297 nan 0.0500 0.0018
## 8 0.0287 nan 0.0500 0.0005
## 9 0.0269 nan 0.0500 0.0018
## 10 0.0252 nan 0.0500 0.0007
## 20 0.0155 nan 0.0500 -0.0003
## 40 0.0075 nan 0.0500 0.0001
## 60 0.0039 nan 0.0500 0.0000
## 80 0.0026 nan 0.0500 0.0000
## 100 0.0020 nan 0.0500 0.0000
## 120 0.0013 nan 0.0500 0.0000
## 140 0.0009 nan 0.0500 -0.0000
## 160 0.0006 nan 0.0500 -0.0000
## 180 0.0004 nan 0.0500 0.0000
## 200 0.0003 nan 0.0500 -0.0000
##
## - Fold23: shrinkage=0.05, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold23: shrinkage=0.05, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0418 nan 0.0500 0.0020
## 2 0.0385 nan 0.0500 0.0020
## 3 0.0358 nan 0.0500 0.0022
## 4 0.0325 nan 0.0500 0.0027
## 5 0.0288 nan 0.0500 0.0042
## 6 0.0265 nan 0.0500 0.0017
## 7 0.0246 nan 0.0500 0.0016
## 8 0.0228 nan 0.0500 0.0014
## 9 0.0218 nan 0.0500 0.0007
## 10 0.0200 nan 0.0500 0.0011
## 20 0.0096 nan 0.0500 0.0001
## 40 0.0028 nan 0.0500 0.0001
## 60 0.0010 nan 0.0500 0.0000
## 80 0.0004 nan 0.0500 0.0000
## 100 0.0002 nan 0.0500 0.0000
## 120 0.0001 nan 0.0500 -0.0000
## 140 0.0000 nan 0.0500 -0.0000
## 160 0.0000 nan 0.0500 0.0000
## 180 0.0000 nan 0.0500 -0.0000
## 200 0.0000 nan 0.0500 -0.0000
##
## - Fold23: shrinkage=0.05, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold23: shrinkage=0.05, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0408 nan 0.0500 0.0031
## 2 0.0381 nan 0.0500 0.0024
## 3 0.0355 nan 0.0500 0.0031
## 4 0.0338 nan 0.0500 0.0008
## 5 0.0314 nan 0.0500 0.0021
## 6 0.0295 nan 0.0500 0.0015
## 7 0.0280 nan 0.0500 0.0017
## 8 0.0260 nan 0.0500 0.0018
## 9 0.0240 nan 0.0500 0.0015
## 10 0.0221 nan 0.0500 0.0017
## 20 0.0119 nan 0.0500 0.0009
## 40 0.0036 nan 0.0500 0.0001
## 60 0.0015 nan 0.0500 -0.0000
## 80 0.0007 nan 0.0500 -0.0000
## 100 0.0004 nan 0.0500 0.0000
## 120 0.0003 nan 0.0500 0.0000
## 140 0.0002 nan 0.0500 0.0000
## 160 0.0001 nan 0.0500 -0.0000
## 180 0.0001 nan 0.0500 -0.0000
## 200 0.0001 nan 0.0500 -0.0000
##
## - Fold23: shrinkage=0.05, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold23: shrinkage=0.05, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0413 nan 0.0500 0.0026
## 2 0.0391 nan 0.0500 0.0025
## 3 0.0370 nan 0.0500 0.0013
## 4 0.0348 nan 0.0500 0.0019
## 5 0.0325 nan 0.0500 0.0020
## 6 0.0306 nan 0.0500 0.0014
## 7 0.0293 nan 0.0500 0.0004
## 8 0.0285 nan 0.0500 0.0002
## 9 0.0267 nan 0.0500 0.0017
## 10 0.0256 nan 0.0500 0.0006
## 20 0.0166 nan 0.0500 0.0004
## 40 0.0084 nan 0.0500 0.0001
## 60 0.0048 nan 0.0500 0.0001
## 80 0.0029 nan 0.0500 0.0000
## 100 0.0021 nan 0.0500 0.0000
## 120 0.0016 nan 0.0500 -0.0000
## 140 0.0011 nan 0.0500 0.0000
## 160 0.0009 nan 0.0500 -0.0000
## 180 0.0007 nan 0.0500 0.0000
## 200 0.0005 nan 0.0500 0.0000
##
## - Fold23: shrinkage=0.05, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold23: shrinkage=0.10, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0426 nan 0.1000 -0.0003
## 2 0.0389 nan 0.1000 0.0021
## 3 0.0331 nan 0.1000 0.0063
## 4 0.0289 nan 0.1000 0.0042
## 5 0.0251 nan 0.1000 0.0010
## 6 0.0217 nan 0.1000 0.0018
## 7 0.0182 nan 0.1000 0.0040
## 8 0.0166 nan 0.1000 0.0007
## 9 0.0144 nan 0.1000 0.0014
## 10 0.0126 nan 0.1000 0.0015
## 20 0.0051 nan 0.1000 0.0002
## 40 0.0015 nan 0.1000 -0.0001
## 60 0.0004 nan 0.1000 0.0000
## 80 0.0002 nan 0.1000 -0.0000
## 100 0.0001 nan 0.1000 0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 0.0000
## 200 0.0000 nan 0.1000 0.0000
##
## - Fold23: shrinkage=0.10, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold23: shrinkage=0.10, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0398 nan 0.1000 0.0026
## 2 0.0341 nan 0.1000 0.0047
## 3 0.0290 nan 0.1000 0.0041
## 4 0.0256 nan 0.1000 0.0028
## 5 0.0230 nan 0.1000 0.0020
## 6 0.0212 nan 0.1000 0.0003
## 7 0.0206 nan 0.1000 -0.0003
## 8 0.0184 nan 0.1000 0.0002
## 9 0.0178 nan 0.1000 -0.0006
## 10 0.0170 nan 0.1000 -0.0000
## 20 0.0069 nan 0.1000 0.0001
## 40 0.0018 nan 0.1000 -0.0001
## 60 0.0007 nan 0.1000 0.0000
## 80 0.0003 nan 0.1000 -0.0000
## 100 0.0002 nan 0.1000 0.0000
## 120 0.0001 nan 0.1000 -0.0000
## 140 0.0001 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold23: shrinkage=0.10, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold23: shrinkage=0.10, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0405 nan 0.1000 0.0034
## 2 0.0379 nan 0.1000 0.0005
## 3 0.0338 nan 0.1000 0.0035
## 4 0.0313 nan 0.1000 0.0011
## 5 0.0303 nan 0.1000 -0.0003
## 6 0.0288 nan 0.1000 0.0015
## 7 0.0273 nan 0.1000 -0.0009
## 8 0.0237 nan 0.1000 0.0019
## 9 0.0221 nan 0.1000 0.0012
## 10 0.0205 nan 0.1000 0.0010
## 20 0.0095 nan 0.1000 0.0005
## 40 0.0034 nan 0.1000 -0.0001
## 60 0.0017 nan 0.1000 0.0000
## 80 0.0009 nan 0.1000 -0.0000
## 100 0.0004 nan 0.1000 -0.0000
## 120 0.0002 nan 0.1000 -0.0000
## 140 0.0002 nan 0.1000 -0.0000
## 160 0.0001 nan 0.1000 -0.0000
## 180 0.0001 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 0.0000
##
## - Fold23: shrinkage=0.10, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold23: shrinkage=0.10, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0421 nan 0.1000 0.0001
## 2 0.0360 nan 0.1000 0.0050
## 3 0.0296 nan 0.1000 0.0024
## 4 0.0263 nan 0.1000 0.0027
## 5 0.0235 nan 0.1000 0.0019
## 6 0.0196 nan 0.1000 0.0029
## 7 0.0174 nan 0.1000 0.0020
## 8 0.0160 nan 0.1000 0.0015
## 9 0.0139 nan 0.1000 0.0014
## 10 0.0123 nan 0.1000 0.0009
## 20 0.0040 nan 0.1000 0.0001
## 40 0.0006 nan 0.1000 -0.0000
## 60 0.0002 nan 0.1000 0.0000
## 80 0.0000 nan 0.1000 -0.0000
## 100 0.0000 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold23: shrinkage=0.10, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold23: shrinkage=0.10, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0383 nan 0.1000 0.0050
## 2 0.0316 nan 0.1000 0.0054
## 3 0.0267 nan 0.1000 0.0030
## 4 0.0223 nan 0.1000 0.0026
## 5 0.0187 nan 0.1000 0.0029
## 6 0.0169 nan 0.1000 0.0023
## 7 0.0139 nan 0.1000 0.0020
## 8 0.0123 nan 0.1000 0.0010
## 9 0.0109 nan 0.1000 0.0011
## 10 0.0097 nan 0.1000 0.0012
## 20 0.0029 nan 0.1000 0.0001
## 40 0.0007 nan 0.1000 -0.0000
## 60 0.0002 nan 0.1000 -0.0000
## 80 0.0001 nan 0.1000 -0.0000
## 100 0.0001 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold23: shrinkage=0.10, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold23: shrinkage=0.10, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0391 nan 0.1000 0.0056
## 2 0.0382 nan 0.1000 -0.0029
## 3 0.0343 nan 0.1000 0.0042
## 4 0.0307 nan 0.1000 0.0040
## 5 0.0264 nan 0.1000 0.0031
## 6 0.0234 nan 0.1000 0.0026
## 7 0.0206 nan 0.1000 0.0021
## 8 0.0186 nan 0.1000 0.0019
## 9 0.0167 nan 0.1000 0.0019
## 10 0.0151 nan 0.1000 0.0008
## 20 0.0075 nan 0.1000 0.0000
## 40 0.0030 nan 0.1000 -0.0000
## 60 0.0014 nan 0.1000 -0.0000
## 80 0.0007 nan 0.1000 -0.0001
## 100 0.0004 nan 0.1000 -0.0000
## 120 0.0002 nan 0.1000 -0.0000
## 140 0.0001 nan 0.1000 0.0000
## 160 0.0001 nan 0.1000 0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold23: shrinkage=0.10, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold23: shrinkage=0.10, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0379 nan 0.1000 0.0054
## 2 0.0321 nan 0.1000 0.0064
## 3 0.0300 nan 0.1000 0.0002
## 4 0.0256 nan 0.1000 0.0038
## 5 0.0220 nan 0.1000 0.0031
## 6 0.0193 nan 0.1000 0.0018
## 7 0.0169 nan 0.1000 0.0002
## 8 0.0153 nan 0.1000 0.0009
## 9 0.0128 nan 0.1000 0.0010
## 10 0.0110 nan 0.1000 0.0016
## 20 0.0026 nan 0.1000 0.0001
## 40 0.0004 nan 0.1000 -0.0000
## 60 0.0001 nan 0.1000 -0.0000
## 80 0.0000 nan 0.1000 -0.0000
## 100 0.0000 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold23: shrinkage=0.10, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold23: shrinkage=0.10, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0401 nan 0.1000 0.0028
## 2 0.0344 nan 0.1000 0.0038
## 3 0.0291 nan 0.1000 0.0045
## 4 0.0259 nan 0.1000 0.0026
## 5 0.0229 nan 0.1000 0.0028
## 6 0.0192 nan 0.1000 0.0021
## 7 0.0173 nan 0.1000 0.0001
## 8 0.0162 nan 0.1000 -0.0010
## 9 0.0141 nan 0.1000 0.0019
## 10 0.0128 nan 0.1000 0.0009
## 20 0.0042 nan 0.1000 0.0001
## 40 0.0008 nan 0.1000 -0.0000
## 60 0.0004 nan 0.1000 0.0000
## 80 0.0002 nan 0.1000 0.0000
## 100 0.0001 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold23: shrinkage=0.10, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold23: shrinkage=0.10, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0385 nan 0.1000 0.0049
## 2 0.0327 nan 0.1000 0.0040
## 3 0.0304 nan 0.1000 0.0017
## 4 0.0267 nan 0.1000 0.0036
## 5 0.0251 nan 0.1000 0.0010
## 6 0.0234 nan 0.1000 0.0017
## 7 0.0216 nan 0.1000 0.0014
## 8 0.0203 nan 0.1000 0.0015
## 9 0.0182 nan 0.1000 0.0018
## 10 0.0165 nan 0.1000 0.0013
## 20 0.0073 nan 0.1000 -0.0000
## 40 0.0031 nan 0.1000 -0.0001
## 60 0.0015 nan 0.1000 -0.0000
## 80 0.0008 nan 0.1000 -0.0000
## 100 0.0005 nan 0.1000 -0.0000
## 120 0.0003 nan 0.1000 -0.0000
## 140 0.0002 nan 0.1000 -0.0000
## 160 0.0001 nan 0.1000 -0.0000
## 180 0.0001 nan 0.1000 -0.0000
## 200 0.0001 nan 0.1000 -0.0000
##
## - Fold23: shrinkage=0.10, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold24: shrinkage=0.01, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0429 nan 0.0100 -0.0001
## 2 0.0423 nan 0.0100 0.0006
## 3 0.0417 nan 0.0100 0.0003
## 4 0.0415 nan 0.0100 -0.0002
## 5 0.0411 nan 0.0100 0.0001
## 6 0.0406 nan 0.0100 0.0005
## 7 0.0401 nan 0.0100 0.0002
## 8 0.0396 nan 0.0100 0.0004
## 9 0.0392 nan 0.0100 0.0002
## 10 0.0389 nan 0.0100 0.0003
## 20 0.0344 nan 0.0100 0.0005
## 40 0.0281 nan 0.0100 0.0002
## 60 0.0227 nan 0.0100 0.0001
## 80 0.0183 nan 0.0100 0.0002
## 100 0.0149 nan 0.0100 0.0001
## 120 0.0128 nan 0.0100 0.0001
## 140 0.0106 nan 0.0100 0.0000
## 160 0.0089 nan 0.0100 0.0000
## 180 0.0077 nan 0.0100 0.0001
## 200 0.0065 nan 0.0100 -0.0000
##
## - Fold24: shrinkage=0.01, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold24: shrinkage=0.01, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0428 nan 0.0100 0.0004
## 2 0.0423 nan 0.0100 0.0005
## 3 0.0417 nan 0.0100 0.0005
## 4 0.0413 nan 0.0100 0.0003
## 5 0.0408 nan 0.0100 0.0003
## 6 0.0404 nan 0.0100 0.0004
## 7 0.0399 nan 0.0100 0.0003
## 8 0.0396 nan 0.0100 0.0001
## 9 0.0392 nan 0.0100 0.0005
## 10 0.0388 nan 0.0100 0.0005
## 20 0.0348 nan 0.0100 0.0004
## 40 0.0280 nan 0.0100 0.0004
## 60 0.0230 nan 0.0100 0.0002
## 80 0.0186 nan 0.0100 0.0002
## 100 0.0155 nan 0.0100 0.0001
## 120 0.0131 nan 0.0100 0.0001
## 140 0.0114 nan 0.0100 0.0000
## 160 0.0099 nan 0.0100 0.0000
## 180 0.0085 nan 0.0100 0.0001
## 200 0.0073 nan 0.0100 0.0000
##
## - Fold24: shrinkage=0.01, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold24: shrinkage=0.01, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0428 nan 0.0100 0.0005
## 2 0.0424 nan 0.0100 0.0003
## 3 0.0420 nan 0.0100 0.0003
## 4 0.0415 nan 0.0100 0.0004
## 5 0.0410 nan 0.0100 0.0004
## 6 0.0403 nan 0.0100 0.0005
## 7 0.0398 nan 0.0100 0.0005
## 8 0.0394 nan 0.0100 0.0004
## 9 0.0389 nan 0.0100 0.0004
## 10 0.0383 nan 0.0100 0.0005
## 20 0.0340 nan 0.0100 0.0004
## 40 0.0274 nan 0.0100 0.0001
## 60 0.0229 nan 0.0100 0.0002
## 80 0.0192 nan 0.0100 0.0000
## 100 0.0163 nan 0.0100 0.0001
## 120 0.0138 nan 0.0100 0.0001
## 140 0.0118 nan 0.0100 0.0001
## 160 0.0104 nan 0.0100 0.0000
## 180 0.0091 nan 0.0100 0.0000
## 200 0.0082 nan 0.0100 0.0000
##
## - Fold24: shrinkage=0.01, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold24: shrinkage=0.01, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0426 nan 0.0100 0.0007
## 2 0.0419 nan 0.0100 0.0006
## 3 0.0414 nan 0.0100 0.0002
## 4 0.0411 nan 0.0100 0.0002
## 5 0.0405 nan 0.0100 0.0000
## 6 0.0400 nan 0.0100 0.0005
## 7 0.0392 nan 0.0100 0.0006
## 8 0.0387 nan 0.0100 0.0006
## 9 0.0380 nan 0.0100 0.0006
## 10 0.0377 nan 0.0100 -0.0002
## 20 0.0329 nan 0.0100 0.0002
## 40 0.0258 nan 0.0100 0.0001
## 60 0.0203 nan 0.0100 0.0002
## 80 0.0155 nan 0.0100 0.0002
## 100 0.0122 nan 0.0100 0.0001
## 120 0.0099 nan 0.0100 -0.0000
## 140 0.0078 nan 0.0100 0.0001
## 160 0.0063 nan 0.0100 0.0000
## 180 0.0051 nan 0.0100 0.0000
## 200 0.0042 nan 0.0100 0.0000
##
## - Fold24: shrinkage=0.01, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold24: shrinkage=0.01, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0429 nan 0.0100 0.0001
## 2 0.0422 nan 0.0100 0.0005
## 3 0.0416 nan 0.0100 0.0007
## 4 0.0412 nan 0.0100 0.0000
## 5 0.0407 nan 0.0100 0.0003
## 6 0.0401 nan 0.0100 0.0004
## 7 0.0397 nan 0.0100 0.0003
## 8 0.0393 nan 0.0100 0.0004
## 9 0.0389 nan 0.0100 0.0004
## 10 0.0383 nan 0.0100 0.0003
## 20 0.0335 nan 0.0100 0.0002
## 40 0.0262 nan 0.0100 0.0004
## 60 0.0207 nan 0.0100 0.0001
## 80 0.0163 nan 0.0100 0.0001
## 100 0.0129 nan 0.0100 0.0001
## 120 0.0100 nan 0.0100 0.0000
## 140 0.0081 nan 0.0100 0.0000
## 160 0.0065 nan 0.0100 -0.0000
## 180 0.0054 nan 0.0100 0.0000
## 200 0.0045 nan 0.0100 0.0000
##
## - Fold24: shrinkage=0.01, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold24: shrinkage=0.01, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0428 nan 0.0100 0.0004
## 2 0.0423 nan 0.0100 0.0005
## 3 0.0417 nan 0.0100 0.0005
## 4 0.0412 nan 0.0100 0.0005
## 5 0.0406 nan 0.0100 0.0002
## 6 0.0403 nan 0.0100 0.0002
## 7 0.0397 nan 0.0100 0.0005
## 8 0.0393 nan 0.0100 0.0003
## 9 0.0390 nan 0.0100 -0.0000
## 10 0.0387 nan 0.0100 0.0004
## 20 0.0347 nan 0.0100 0.0002
## 40 0.0276 nan 0.0100 0.0003
## 60 0.0229 nan 0.0100 0.0002
## 80 0.0187 nan 0.0100 0.0002
## 100 0.0160 nan 0.0100 0.0001
## 120 0.0138 nan 0.0100 0.0001
## 140 0.0121 nan 0.0100 0.0001
## 160 0.0108 nan 0.0100 0.0000
## 180 0.0099 nan 0.0100 -0.0000
## 200 0.0090 nan 0.0100 0.0000
##
## - Fold24: shrinkage=0.01, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold24: shrinkage=0.01, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0427 nan 0.0100 0.0002
## 2 0.0423 nan 0.0100 0.0003
## 3 0.0417 nan 0.0100 0.0007
## 4 0.0410 nan 0.0100 0.0003
## 5 0.0406 nan 0.0100 0.0004
## 6 0.0400 nan 0.0100 0.0006
## 7 0.0394 nan 0.0100 0.0004
## 8 0.0389 nan 0.0100 0.0002
## 9 0.0385 nan 0.0100 0.0003
## 10 0.0378 nan 0.0100 0.0005
## 20 0.0327 nan 0.0100 0.0005
## 40 0.0249 nan 0.0100 0.0003
## 60 0.0190 nan 0.0100 0.0002
## 80 0.0149 nan 0.0100 0.0001
## 100 0.0116 nan 0.0100 0.0002
## 120 0.0088 nan 0.0100 0.0001
## 140 0.0070 nan 0.0100 -0.0000
## 160 0.0055 nan 0.0100 0.0000
## 180 0.0045 nan 0.0100 0.0000
## 200 0.0035 nan 0.0100 0.0000
##
## - Fold24: shrinkage=0.01, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold24: shrinkage=0.01, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0425 nan 0.0100 0.0004
## 2 0.0420 nan 0.0100 0.0004
## 3 0.0415 nan 0.0100 0.0004
## 4 0.0409 nan 0.0100 0.0004
## 5 0.0402 nan 0.0100 0.0005
## 6 0.0394 nan 0.0100 0.0007
## 7 0.0388 nan 0.0100 0.0003
## 8 0.0383 nan 0.0100 0.0004
## 9 0.0380 nan 0.0100 0.0003
## 10 0.0374 nan 0.0100 0.0006
## 20 0.0322 nan 0.0100 0.0004
## 40 0.0247 nan 0.0100 0.0002
## 60 0.0193 nan 0.0100 0.0001
## 80 0.0153 nan 0.0100 0.0001
## 100 0.0121 nan 0.0100 0.0000
## 120 0.0096 nan 0.0100 0.0001
## 140 0.0077 nan 0.0100 0.0000
## 160 0.0063 nan 0.0100 0.0000
## 180 0.0052 nan 0.0100 -0.0000
## 200 0.0043 nan 0.0100 0.0000
##
## - Fold24: shrinkage=0.01, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold24: shrinkage=0.01, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0428 nan 0.0100 0.0002
## 2 0.0424 nan 0.0100 0.0005
## 3 0.0417 nan 0.0100 0.0005
## 4 0.0412 nan 0.0100 0.0005
## 5 0.0408 nan 0.0100 0.0001
## 6 0.0403 nan 0.0100 0.0005
## 7 0.0399 nan 0.0100 0.0004
## 8 0.0393 nan 0.0100 0.0005
## 9 0.0388 nan 0.0100 0.0002
## 10 0.0383 nan 0.0100 0.0005
## 20 0.0348 nan 0.0100 0.0003
## 40 0.0276 nan 0.0100 0.0000
## 60 0.0225 nan 0.0100 -0.0000
## 80 0.0188 nan 0.0100 0.0001
## 100 0.0159 nan 0.0100 0.0001
## 120 0.0137 nan 0.0100 0.0001
## 140 0.0119 nan 0.0100 -0.0000
## 160 0.0103 nan 0.0100 0.0000
## 180 0.0092 nan 0.0100 0.0000
## 200 0.0081 nan 0.0100 0.0000
##
## - Fold24: shrinkage=0.01, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold24: shrinkage=0.05, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0398 nan 0.0500 0.0029
## 2 0.0368 nan 0.0500 0.0029
## 3 0.0348 nan 0.0500 0.0016
## 4 0.0334 nan 0.0500 0.0014
## 5 0.0317 nan 0.0500 0.0012
## 6 0.0310 nan 0.0500 -0.0003
## 7 0.0298 nan 0.0500 0.0007
## 8 0.0284 nan 0.0500 0.0009
## 9 0.0268 nan 0.0500 0.0005
## 10 0.0255 nan 0.0500 0.0012
## 20 0.0152 nan 0.0500 0.0008
## 40 0.0065 nan 0.0500 0.0002
## 60 0.0031 nan 0.0500 0.0001
## 80 0.0016 nan 0.0500 0.0000
## 100 0.0009 nan 0.0500 -0.0000
## 120 0.0006 nan 0.0500 0.0000
## 140 0.0004 nan 0.0500 -0.0000
## 160 0.0002 nan 0.0500 0.0000
## 180 0.0001 nan 0.0500 0.0000
## 200 0.0001 nan 0.0500 -0.0000
##
## - Fold24: shrinkage=0.05, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold24: shrinkage=0.05, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0409 nan 0.0500 0.0005
## 2 0.0385 nan 0.0500 0.0006
## 3 0.0359 nan 0.0500 0.0027
## 4 0.0341 nan 0.0500 0.0014
## 5 0.0320 nan 0.0500 0.0017
## 6 0.0304 nan 0.0500 0.0019
## 7 0.0284 nan 0.0500 0.0020
## 8 0.0271 nan 0.0500 0.0008
## 9 0.0253 nan 0.0500 0.0014
## 10 0.0236 nan 0.0500 0.0016
## 20 0.0149 nan 0.0500 0.0001
## 40 0.0063 nan 0.0500 -0.0000
## 60 0.0033 nan 0.0500 0.0001
## 80 0.0020 nan 0.0500 0.0000
## 100 0.0013 nan 0.0500 -0.0001
## 120 0.0009 nan 0.0500 -0.0000
## 140 0.0006 nan 0.0500 -0.0000
## 160 0.0004 nan 0.0500 0.0000
## 180 0.0003 nan 0.0500 -0.0000
## 200 0.0003 nan 0.0500 -0.0000
##
## - Fold24: shrinkage=0.05, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold24: shrinkage=0.05, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0410 nan 0.0500 0.0014
## 2 0.0382 nan 0.0500 0.0027
## 3 0.0354 nan 0.0500 0.0026
## 4 0.0328 nan 0.0500 0.0021
## 5 0.0304 nan 0.0500 0.0018
## 6 0.0289 nan 0.0500 0.0015
## 7 0.0276 nan 0.0500 0.0010
## 8 0.0264 nan 0.0500 0.0007
## 9 0.0252 nan 0.0500 0.0011
## 10 0.0243 nan 0.0500 0.0007
## 20 0.0151 nan 0.0500 0.0004
## 40 0.0074 nan 0.0500 -0.0001
## 60 0.0043 nan 0.0500 0.0000
## 80 0.0026 nan 0.0500 -0.0001
## 100 0.0019 nan 0.0500 0.0000
## 120 0.0012 nan 0.0500 0.0000
## 140 0.0008 nan 0.0500 -0.0000
## 160 0.0006 nan 0.0500 -0.0000
## 180 0.0005 nan 0.0500 -0.0000
## 200 0.0003 nan 0.0500 0.0000
##
## - Fold24: shrinkage=0.05, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold24: shrinkage=0.05, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0396 nan 0.0500 0.0042
## 2 0.0376 nan 0.0500 0.0021
## 3 0.0356 nan 0.0500 0.0009
## 4 0.0322 nan 0.0500 0.0035
## 5 0.0299 nan 0.0500 0.0010
## 6 0.0276 nan 0.0500 0.0015
## 7 0.0256 nan 0.0500 0.0009
## 8 0.0248 nan 0.0500 0.0007
## 9 0.0231 nan 0.0500 0.0013
## 10 0.0218 nan 0.0500 0.0011
## 20 0.0124 nan 0.0500 -0.0001
## 40 0.0044 nan 0.0500 0.0002
## 60 0.0018 nan 0.0500 -0.0001
## 80 0.0009 nan 0.0500 0.0000
## 100 0.0004 nan 0.0500 -0.0000
## 120 0.0003 nan 0.0500 0.0000
## 140 0.0002 nan 0.0500 0.0000
## 160 0.0001 nan 0.0500 -0.0000
## 180 0.0000 nan 0.0500 -0.0000
## 200 0.0000 nan 0.0500 0.0000
##
## - Fold24: shrinkage=0.05, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold24: shrinkage=0.05, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0411 nan 0.0500 0.0024
## 2 0.0387 nan 0.0500 0.0009
## 3 0.0372 nan 0.0500 0.0012
## 4 0.0342 nan 0.0500 0.0027
## 5 0.0333 nan 0.0500 0.0003
## 6 0.0307 nan 0.0500 0.0020
## 7 0.0284 nan 0.0500 0.0023
## 8 0.0267 nan 0.0500 0.0011
## 9 0.0249 nan 0.0500 0.0018
## 10 0.0232 nan 0.0500 0.0012
## 20 0.0130 nan 0.0500 0.0004
## 40 0.0046 nan 0.0500 0.0002
## 60 0.0022 nan 0.0500 0.0000
## 80 0.0011 nan 0.0500 -0.0000
## 100 0.0006 nan 0.0500 0.0000
## 120 0.0004 nan 0.0500 -0.0000
## 140 0.0002 nan 0.0500 -0.0000
## 160 0.0001 nan 0.0500 -0.0000
## 180 0.0001 nan 0.0500 -0.0000
## 200 0.0001 nan 0.0500 0.0000
##
## - Fold24: shrinkage=0.05, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold24: shrinkage=0.05, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0404 nan 0.0500 0.0029
## 2 0.0387 nan 0.0500 0.0012
## 3 0.0368 nan 0.0500 0.0019
## 4 0.0357 nan 0.0500 0.0012
## 5 0.0338 nan 0.0500 0.0010
## 6 0.0321 nan 0.0500 0.0008
## 7 0.0300 nan 0.0500 0.0018
## 8 0.0283 nan 0.0500 0.0017
## 9 0.0268 nan 0.0500 0.0010
## 10 0.0251 nan 0.0500 0.0014
## 20 0.0163 nan 0.0500 0.0001
## 40 0.0085 nan 0.0500 -0.0002
## 60 0.0053 nan 0.0500 -0.0001
## 80 0.0036 nan 0.0500 0.0000
## 100 0.0024 nan 0.0500 0.0000
## 120 0.0017 nan 0.0500 0.0000
## 140 0.0013 nan 0.0500 -0.0000
## 160 0.0009 nan 0.0500 -0.0000
## 180 0.0006 nan 0.0500 0.0000
## 200 0.0005 nan 0.0500 -0.0000
##
## - Fold24: shrinkage=0.05, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold24: shrinkage=0.05, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0407 nan 0.0500 0.0011
## 2 0.0377 nan 0.0500 0.0019
## 3 0.0343 nan 0.0500 0.0019
## 4 0.0321 nan 0.0500 0.0013
## 5 0.0292 nan 0.0500 0.0022
## 6 0.0288 nan 0.0500 -0.0003
## 7 0.0264 nan 0.0500 0.0019
## 8 0.0250 nan 0.0500 0.0012
## 9 0.0233 nan 0.0500 0.0015
## 10 0.0209 nan 0.0500 0.0016
## 20 0.0104 nan 0.0500 0.0006
## 40 0.0031 nan 0.0500 0.0001
## 60 0.0011 nan 0.0500 -0.0000
## 80 0.0004 nan 0.0500 -0.0000
## 100 0.0002 nan 0.0500 0.0000
## 120 0.0001 nan 0.0500 -0.0000
## 140 0.0000 nan 0.0500 0.0000
## 160 0.0000 nan 0.0500 -0.0000
## 180 0.0000 nan 0.0500 0.0000
## 200 0.0000 nan 0.0500 -0.0000
##
## - Fold24: shrinkage=0.05, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold24: shrinkage=0.05, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0391 nan 0.0500 0.0038
## 2 0.0360 nan 0.0500 0.0018
## 3 0.0329 nan 0.0500 0.0026
## 4 0.0298 nan 0.0500 0.0027
## 5 0.0272 nan 0.0500 0.0020
## 6 0.0257 nan 0.0500 0.0014
## 7 0.0241 nan 0.0500 0.0013
## 8 0.0234 nan 0.0500 0.0004
## 9 0.0216 nan 0.0500 0.0009
## 10 0.0201 nan 0.0500 0.0012
## 20 0.0116 nan 0.0500 0.0002
## 40 0.0043 nan 0.0500 0.0001
## 60 0.0022 nan 0.0500 0.0000
## 80 0.0011 nan 0.0500 -0.0000
## 100 0.0006 nan 0.0500 -0.0000
## 120 0.0004 nan 0.0500 -0.0000
## 140 0.0003 nan 0.0500 0.0000
## 160 0.0002 nan 0.0500 -0.0000
## 180 0.0001 nan 0.0500 0.0000
## 200 0.0001 nan 0.0500 -0.0000
##
## - Fold24: shrinkage=0.05, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold24: shrinkage=0.05, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0416 nan 0.0500 0.0012
## 2 0.0390 nan 0.0500 0.0026
## 3 0.0365 nan 0.0500 0.0007
## 4 0.0347 nan 0.0500 -0.0000
## 5 0.0327 nan 0.0500 0.0023
## 6 0.0308 nan 0.0500 0.0019
## 7 0.0297 nan 0.0500 0.0001
## 8 0.0286 nan 0.0500 0.0011
## 9 0.0273 nan 0.0500 0.0013
## 10 0.0263 nan 0.0500 -0.0004
## 20 0.0159 nan 0.0500 0.0001
## 40 0.0081 nan 0.0500 0.0002
## 60 0.0045 nan 0.0500 0.0001
## 80 0.0028 nan 0.0500 0.0001
## 100 0.0019 nan 0.0500 0.0000
## 120 0.0013 nan 0.0500 -0.0000
## 140 0.0009 nan 0.0500 -0.0000
## 160 0.0007 nan 0.0500 -0.0000
## 180 0.0005 nan 0.0500 0.0000
## 200 0.0004 nan 0.0500 -0.0000
##
## - Fold24: shrinkage=0.05, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold24: shrinkage=0.10, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0379 nan 0.1000 0.0034
## 2 0.0330 nan 0.1000 0.0045
## 3 0.0284 nan 0.1000 0.0043
## 4 0.0261 nan 0.1000 0.0025
## 5 0.0243 nan 0.1000 -0.0002
## 6 0.0216 nan 0.1000 0.0006
## 7 0.0197 nan 0.1000 -0.0007
## 8 0.0177 nan 0.1000 0.0011
## 9 0.0164 nan 0.1000 0.0009
## 10 0.0153 nan 0.1000 0.0004
## 20 0.0071 nan 0.1000 -0.0002
## 40 0.0019 nan 0.1000 0.0001
## 60 0.0006 nan 0.1000 -0.0000
## 80 0.0002 nan 0.1000 -0.0000
## 100 0.0001 nan 0.1000 0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 0.0000
##
## - Fold24: shrinkage=0.10, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold24: shrinkage=0.10, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0384 nan 0.1000 0.0047
## 2 0.0348 nan 0.1000 0.0015
## 3 0.0311 nan 0.1000 0.0031
## 4 0.0280 nan 0.1000 0.0019
## 5 0.0264 nan 0.1000 0.0013
## 6 0.0239 nan 0.1000 0.0025
## 7 0.0212 nan 0.1000 0.0022
## 8 0.0208 nan 0.1000 -0.0018
## 9 0.0188 nan 0.1000 0.0018
## 10 0.0169 nan 0.1000 0.0014
## 20 0.0077 nan 0.1000 -0.0000
## 40 0.0031 nan 0.1000 0.0002
## 60 0.0010 nan 0.1000 -0.0000
## 80 0.0004 nan 0.1000 0.0000
## 100 0.0002 nan 0.1000 0.0000
## 120 0.0001 nan 0.1000 0.0000
## 140 0.0001 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold24: shrinkage=0.10, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold24: shrinkage=0.10, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0370 nan 0.1000 0.0056
## 2 0.0327 nan 0.1000 0.0029
## 3 0.0277 nan 0.1000 0.0040
## 4 0.0243 nan 0.1000 0.0003
## 5 0.0216 nan 0.1000 0.0024
## 6 0.0193 nan 0.1000 0.0022
## 7 0.0178 nan 0.1000 0.0011
## 8 0.0163 nan 0.1000 0.0017
## 9 0.0152 nan 0.1000 0.0002
## 10 0.0134 nan 0.1000 0.0009
## 20 0.0068 nan 0.1000 -0.0001
## 40 0.0030 nan 0.1000 0.0001
## 60 0.0014 nan 0.1000 -0.0001
## 80 0.0008 nan 0.1000 -0.0001
## 100 0.0005 nan 0.1000 -0.0000
## 120 0.0003 nan 0.1000 -0.0000
## 140 0.0002 nan 0.1000 -0.0000
## 160 0.0001 nan 0.1000 -0.0000
## 180 0.0001 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold24: shrinkage=0.10, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold24: shrinkage=0.10, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0359 nan 0.1000 0.0046
## 2 0.0304 nan 0.1000 0.0041
## 3 0.0257 nan 0.1000 0.0045
## 4 0.0232 nan 0.1000 0.0017
## 5 0.0197 nan 0.1000 0.0028
## 6 0.0181 nan 0.1000 0.0005
## 7 0.0174 nan 0.1000 -0.0003
## 8 0.0148 nan 0.1000 0.0023
## 9 0.0130 nan 0.1000 0.0002
## 10 0.0115 nan 0.1000 0.0015
## 20 0.0032 nan 0.1000 0.0002
## 40 0.0006 nan 0.1000 -0.0000
## 60 0.0002 nan 0.1000 -0.0000
## 80 0.0001 nan 0.1000 -0.0000
## 100 0.0000 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold24: shrinkage=0.10, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold24: shrinkage=0.10, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0361 nan 0.1000 0.0036
## 2 0.0309 nan 0.1000 0.0045
## 3 0.0296 nan 0.1000 -0.0002
## 4 0.0255 nan 0.1000 0.0021
## 5 0.0210 nan 0.1000 0.0017
## 6 0.0176 nan 0.1000 0.0029
## 7 0.0153 nan 0.1000 0.0019
## 8 0.0140 nan 0.1000 0.0010
## 9 0.0130 nan 0.1000 -0.0002
## 10 0.0120 nan 0.1000 0.0006
## 20 0.0045 nan 0.1000 0.0000
## 40 0.0011 nan 0.1000 -0.0000
## 60 0.0003 nan 0.1000 -0.0000
## 80 0.0001 nan 0.1000 -0.0000
## 100 0.0001 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold24: shrinkage=0.10, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold24: shrinkage=0.10, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0395 nan 0.1000 0.0031
## 2 0.0329 nan 0.1000 0.0047
## 3 0.0295 nan 0.1000 0.0013
## 4 0.0256 nan 0.1000 0.0034
## 5 0.0238 nan 0.1000 0.0018
## 6 0.0215 nan 0.1000 0.0022
## 7 0.0197 nan 0.1000 0.0018
## 8 0.0181 nan 0.1000 0.0006
## 9 0.0165 nan 0.1000 -0.0007
## 10 0.0151 nan 0.1000 0.0009
## 20 0.0070 nan 0.1000 0.0001
## 40 0.0026 nan 0.1000 -0.0002
## 60 0.0011 nan 0.1000 0.0000
## 80 0.0005 nan 0.1000 -0.0000
## 100 0.0003 nan 0.1000 -0.0000
## 120 0.0001 nan 0.1000 0.0000
## 140 0.0001 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 0.0000
## 180 0.0000 nan 0.1000 0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold24: shrinkage=0.10, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold24: shrinkage=0.10, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0378 nan 0.1000 0.0044
## 2 0.0315 nan 0.1000 0.0019
## 3 0.0277 nan 0.1000 0.0024
## 4 0.0233 nan 0.1000 0.0030
## 5 0.0207 nan 0.1000 0.0020
## 6 0.0192 nan 0.1000 0.0003
## 7 0.0172 nan 0.1000 0.0012
## 8 0.0145 nan 0.1000 0.0020
## 9 0.0126 nan 0.1000 0.0016
## 10 0.0107 nan 0.1000 0.0011
## 20 0.0033 nan 0.1000 0.0000
## 40 0.0005 nan 0.1000 -0.0000
## 60 0.0001 nan 0.1000 -0.0000
## 80 0.0000 nan 0.1000 -0.0000
## 100 0.0000 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold24: shrinkage=0.10, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold24: shrinkage=0.10, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0394 nan 0.1000 0.0024
## 2 0.0352 nan 0.1000 0.0023
## 3 0.0307 nan 0.1000 0.0034
## 4 0.0283 nan 0.1000 0.0007
## 5 0.0244 nan 0.1000 0.0039
## 6 0.0217 nan 0.1000 0.0021
## 7 0.0191 nan 0.1000 0.0026
## 8 0.0168 nan 0.1000 0.0007
## 9 0.0154 nan 0.1000 0.0010
## 10 0.0132 nan 0.1000 0.0014
## 20 0.0046 nan 0.1000 0.0005
## 40 0.0011 nan 0.1000 0.0001
## 60 0.0004 nan 0.1000 -0.0000
## 80 0.0002 nan 0.1000 -0.0000
## 100 0.0001 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 0.0000
##
## - Fold24: shrinkage=0.10, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold24: shrinkage=0.10, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0403 nan 0.1000 0.0021
## 2 0.0341 nan 0.1000 0.0048
## 3 0.0310 nan 0.1000 0.0014
## 4 0.0272 nan 0.1000 0.0030
## 5 0.0240 nan 0.1000 0.0027
## 6 0.0222 nan 0.1000 0.0013
## 7 0.0209 nan 0.1000 0.0015
## 8 0.0187 nan 0.1000 0.0019
## 9 0.0178 nan 0.1000 0.0007
## 10 0.0172 nan 0.1000 0.0002
## 20 0.0100 nan 0.1000 -0.0003
## 40 0.0039 nan 0.1000 -0.0001
## 60 0.0019 nan 0.1000 0.0000
## 80 0.0008 nan 0.1000 -0.0001
## 100 0.0005 nan 0.1000 -0.0000
## 120 0.0003 nan 0.1000 -0.0000
## 140 0.0002 nan 0.1000 -0.0000
## 160 0.0001 nan 0.1000 -0.0000
## 180 0.0001 nan 0.1000 0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold24: shrinkage=0.10, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold25: shrinkage=0.01, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0392 nan 0.0100 0.0001
## 2 0.0387 nan 0.0100 0.0005
## 3 0.0382 nan 0.0100 0.0003
## 4 0.0378 nan 0.0100 0.0003
## 5 0.0374 nan 0.0100 0.0005
## 6 0.0370 nan 0.0100 0.0003
## 7 0.0366 nan 0.0100 0.0003
## 8 0.0364 nan 0.0100 0.0001
## 9 0.0361 nan 0.0100 0.0000
## 10 0.0357 nan 0.0100 0.0003
## 20 0.0317 nan 0.0100 0.0001
## 40 0.0255 nan 0.0100 0.0002
## 60 0.0205 nan 0.0100 0.0002
## 80 0.0172 nan 0.0100 0.0001
## 100 0.0144 nan 0.0100 0.0001
## 120 0.0119 nan 0.0100 0.0001
## 140 0.0101 nan 0.0100 0.0000
## 160 0.0084 nan 0.0100 0.0001
## 180 0.0071 nan 0.0100 -0.0000
## 200 0.0061 nan 0.0100 -0.0000
##
## - Fold25: shrinkage=0.01, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold25: shrinkage=0.01, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0392 nan 0.0100 0.0002
## 2 0.0386 nan 0.0100 0.0005
## 3 0.0382 nan 0.0100 0.0002
## 4 0.0380 nan 0.0100 -0.0000
## 5 0.0375 nan 0.0100 0.0005
## 6 0.0372 nan 0.0100 0.0002
## 7 0.0366 nan 0.0100 0.0005
## 8 0.0364 nan 0.0100 0.0001
## 9 0.0361 nan 0.0100 -0.0000
## 10 0.0357 nan 0.0100 0.0004
## 20 0.0315 nan 0.0100 0.0002
## 40 0.0256 nan 0.0100 0.0002
## 60 0.0210 nan 0.0100 0.0000
## 80 0.0172 nan 0.0100 0.0002
## 100 0.0146 nan 0.0100 0.0002
## 120 0.0121 nan 0.0100 0.0001
## 140 0.0102 nan 0.0100 0.0001
## 160 0.0086 nan 0.0100 0.0000
## 180 0.0073 nan 0.0100 0.0000
## 200 0.0063 nan 0.0100 0.0000
##
## - Fold25: shrinkage=0.01, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold25: shrinkage=0.01, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0390 nan 0.0100 0.0005
## 2 0.0385 nan 0.0100 0.0003
## 3 0.0380 nan 0.0100 0.0005
## 4 0.0377 nan 0.0100 0.0001
## 5 0.0376 nan 0.0100 -0.0000
## 6 0.0372 nan 0.0100 -0.0000
## 7 0.0368 nan 0.0100 0.0002
## 8 0.0363 nan 0.0100 0.0005
## 9 0.0358 nan 0.0100 0.0003
## 10 0.0354 nan 0.0100 0.0003
## 20 0.0316 nan 0.0100 0.0004
## 40 0.0254 nan 0.0100 0.0003
## 60 0.0210 nan 0.0100 -0.0000
## 80 0.0176 nan 0.0100 0.0001
## 100 0.0152 nan 0.0100 -0.0001
## 120 0.0132 nan 0.0100 0.0001
## 140 0.0116 nan 0.0100 -0.0000
## 160 0.0103 nan 0.0100 0.0000
## 180 0.0092 nan 0.0100 0.0000
## 200 0.0084 nan 0.0100 0.0000
##
## - Fold25: shrinkage=0.01, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold25: shrinkage=0.01, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0391 nan 0.0100 0.0003
## 2 0.0386 nan 0.0100 0.0005
## 3 0.0380 nan 0.0100 0.0003
## 4 0.0374 nan 0.0100 0.0004
## 5 0.0371 nan 0.0100 0.0004
## 6 0.0367 nan 0.0100 0.0004
## 7 0.0363 nan 0.0100 0.0003
## 8 0.0360 nan 0.0100 0.0002
## 9 0.0354 nan 0.0100 0.0006
## 10 0.0349 nan 0.0100 0.0004
## 20 0.0309 nan 0.0100 0.0003
## 40 0.0236 nan 0.0100 0.0002
## 60 0.0186 nan 0.0100 -0.0000
## 80 0.0147 nan 0.0100 0.0002
## 100 0.0120 nan 0.0100 0.0000
## 120 0.0093 nan 0.0100 0.0001
## 140 0.0075 nan 0.0100 0.0001
## 160 0.0064 nan 0.0100 0.0000
## 180 0.0050 nan 0.0100 0.0000
## 200 0.0041 nan 0.0100 0.0000
##
## - Fold25: shrinkage=0.01, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold25: shrinkage=0.01, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0390 nan 0.0100 0.0005
## 2 0.0384 nan 0.0100 0.0005
## 3 0.0381 nan 0.0100 0.0004
## 4 0.0374 nan 0.0100 0.0006
## 5 0.0369 nan 0.0100 0.0005
## 6 0.0364 nan 0.0100 0.0004
## 7 0.0361 nan 0.0100 0.0003
## 8 0.0357 nan 0.0100 0.0003
## 9 0.0354 nan 0.0100 0.0003
## 10 0.0348 nan 0.0100 0.0002
## 20 0.0305 nan 0.0100 0.0004
## 40 0.0236 nan 0.0100 0.0001
## 60 0.0187 nan 0.0100 0.0003
## 80 0.0151 nan 0.0100 0.0001
## 100 0.0123 nan 0.0100 0.0001
## 120 0.0096 nan 0.0100 0.0001
## 140 0.0079 nan 0.0100 0.0000
## 160 0.0066 nan 0.0100 0.0000
## 180 0.0056 nan 0.0100 0.0000
## 200 0.0048 nan 0.0100 0.0000
##
## - Fold25: shrinkage=0.01, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold25: shrinkage=0.01, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0391 nan 0.0100 0.0005
## 2 0.0387 nan 0.0100 0.0005
## 3 0.0385 nan 0.0100 -0.0002
## 4 0.0381 nan 0.0100 -0.0000
## 5 0.0377 nan 0.0100 0.0004
## 6 0.0373 nan 0.0100 0.0002
## 7 0.0368 nan 0.0100 0.0005
## 8 0.0364 nan 0.0100 0.0005
## 9 0.0359 nan 0.0100 0.0005
## 10 0.0356 nan 0.0100 0.0003
## 20 0.0313 nan 0.0100 0.0004
## 40 0.0252 nan 0.0100 0.0003
## 60 0.0208 nan 0.0100 0.0002
## 80 0.0177 nan 0.0100 0.0002
## 100 0.0151 nan 0.0100 0.0001
## 120 0.0129 nan 0.0100 0.0000
## 140 0.0113 nan 0.0100 0.0000
## 160 0.0100 nan 0.0100 0.0001
## 180 0.0089 nan 0.0100 0.0000
## 200 0.0079 nan 0.0100 0.0000
##
## - Fold25: shrinkage=0.01, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold25: shrinkage=0.01, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0389 nan 0.0100 0.0003
## 2 0.0385 nan 0.0100 0.0002
## 3 0.0380 nan 0.0100 0.0003
## 4 0.0376 nan 0.0100 0.0004
## 5 0.0369 nan 0.0100 0.0003
## 6 0.0365 nan 0.0100 0.0003
## 7 0.0359 nan 0.0100 0.0006
## 8 0.0353 nan 0.0100 0.0005
## 9 0.0350 nan 0.0100 -0.0000
## 10 0.0345 nan 0.0100 0.0002
## 20 0.0299 nan 0.0100 0.0003
## 40 0.0220 nan 0.0100 0.0003
## 60 0.0166 nan 0.0100 0.0002
## 80 0.0133 nan 0.0100 0.0001
## 100 0.0102 nan 0.0100 0.0000
## 120 0.0082 nan 0.0100 0.0000
## 140 0.0065 nan 0.0100 0.0000
## 160 0.0052 nan 0.0100 -0.0000
## 180 0.0040 nan 0.0100 0.0000
## 200 0.0033 nan 0.0100 0.0000
##
## - Fold25: shrinkage=0.01, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold25: shrinkage=0.01, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0391 nan 0.0100 0.0002
## 2 0.0384 nan 0.0100 0.0002
## 3 0.0377 nan 0.0100 0.0004
## 4 0.0375 nan 0.0100 0.0000
## 5 0.0370 nan 0.0100 0.0006
## 6 0.0365 nan 0.0100 0.0003
## 7 0.0360 nan 0.0100 0.0003
## 8 0.0355 nan 0.0100 0.0005
## 9 0.0351 nan 0.0100 0.0004
## 10 0.0345 nan 0.0100 0.0005
## 20 0.0307 nan 0.0100 0.0003
## 40 0.0238 nan 0.0100 0.0002
## 60 0.0183 nan 0.0100 0.0001
## 80 0.0143 nan 0.0100 0.0001
## 100 0.0112 nan 0.0100 0.0001
## 120 0.0091 nan 0.0100 0.0001
## 140 0.0074 nan 0.0100 0.0001
## 160 0.0061 nan 0.0100 0.0000
## 180 0.0052 nan 0.0100 0.0000
## 200 0.0044 nan 0.0100 -0.0000
##
## - Fold25: shrinkage=0.01, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold25: shrinkage=0.01, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0390 nan 0.0100 0.0005
## 2 0.0383 nan 0.0100 0.0006
## 3 0.0379 nan 0.0100 0.0005
## 4 0.0375 nan 0.0100 0.0004
## 5 0.0370 nan 0.0100 0.0005
## 6 0.0365 nan 0.0100 0.0004
## 7 0.0361 nan 0.0100 0.0004
## 8 0.0357 nan 0.0100 0.0002
## 9 0.0354 nan 0.0100 0.0002
## 10 0.0353 nan 0.0100 -0.0001
## 20 0.0315 nan 0.0100 0.0002
## 40 0.0262 nan 0.0100 0.0002
## 60 0.0217 nan 0.0100 -0.0000
## 80 0.0184 nan 0.0100 0.0002
## 100 0.0157 nan 0.0100 0.0000
## 120 0.0137 nan 0.0100 -0.0001
## 140 0.0118 nan 0.0100 0.0000
## 160 0.0105 nan 0.0100 0.0001
## 180 0.0094 nan 0.0100 0.0000
## 200 0.0084 nan 0.0100 0.0000
##
## - Fold25: shrinkage=0.01, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold25: shrinkage=0.05, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0370 nan 0.0500 0.0014
## 2 0.0347 nan 0.0500 0.0010
## 3 0.0330 nan 0.0500 0.0013
## 4 0.0301 nan 0.0500 0.0025
## 5 0.0285 nan 0.0500 0.0016
## 6 0.0271 nan 0.0500 0.0011
## 7 0.0261 nan 0.0500 -0.0006
## 8 0.0245 nan 0.0500 0.0014
## 9 0.0227 nan 0.0500 0.0018
## 10 0.0213 nan 0.0500 0.0013
## 20 0.0130 nan 0.0500 -0.0002
## 40 0.0055 nan 0.0500 0.0000
## 60 0.0029 nan 0.0500 0.0001
## 80 0.0016 nan 0.0500 -0.0000
## 100 0.0010 nan 0.0500 0.0000
## 120 0.0007 nan 0.0500 -0.0000
## 140 0.0004 nan 0.0500 -0.0000
## 160 0.0003 nan 0.0500 0.0000
## 180 0.0002 nan 0.0500 -0.0000
## 200 0.0001 nan 0.0500 -0.0000
##
## - Fold25: shrinkage=0.05, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold25: shrinkage=0.05, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0373 nan 0.0500 0.0010
## 2 0.0349 nan 0.0500 0.0023
## 3 0.0320 nan 0.0500 0.0023
## 4 0.0303 nan 0.0500 0.0016
## 5 0.0293 nan 0.0500 0.0008
## 6 0.0282 nan 0.0500 0.0005
## 7 0.0267 nan 0.0500 0.0007
## 8 0.0252 nan 0.0500 0.0015
## 9 0.0239 nan 0.0500 0.0003
## 10 0.0225 nan 0.0500 0.0012
## 20 0.0141 nan 0.0500 0.0005
## 40 0.0063 nan 0.0500 0.0000
## 60 0.0033 nan 0.0500 0.0000
## 80 0.0018 nan 0.0500 -0.0000
## 100 0.0012 nan 0.0500 0.0000
## 120 0.0008 nan 0.0500 -0.0000
## 140 0.0005 nan 0.0500 0.0000
## 160 0.0003 nan 0.0500 -0.0000
## 180 0.0002 nan 0.0500 0.0000
## 200 0.0002 nan 0.0500 -0.0000
##
## - Fold25: shrinkage=0.05, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold25: shrinkage=0.05, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0365 nan 0.0500 0.0019
## 2 0.0345 nan 0.0500 0.0020
## 3 0.0319 nan 0.0500 0.0021
## 4 0.0301 nan 0.0500 0.0020
## 5 0.0284 nan 0.0500 0.0016
## 6 0.0276 nan 0.0500 0.0006
## 7 0.0268 nan 0.0500 0.0008
## 8 0.0256 nan 0.0500 0.0012
## 9 0.0234 nan 0.0500 0.0013
## 10 0.0222 nan 0.0500 0.0010
## 20 0.0142 nan 0.0500 0.0003
## 40 0.0083 nan 0.0500 0.0002
## 60 0.0054 nan 0.0500 0.0001
## 80 0.0039 nan 0.0500 -0.0000
## 100 0.0027 nan 0.0500 0.0000
## 120 0.0020 nan 0.0500 0.0000
## 140 0.0016 nan 0.0500 -0.0000
## 160 0.0013 nan 0.0500 -0.0000
## 180 0.0010 nan 0.0500 -0.0000
## 200 0.0008 nan 0.0500 -0.0000
##
## - Fold25: shrinkage=0.05, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold25: shrinkage=0.05, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0369 nan 0.0500 0.0025
## 2 0.0343 nan 0.0500 0.0024
## 3 0.0319 nan 0.0500 0.0011
## 4 0.0295 nan 0.0500 0.0006
## 5 0.0275 nan 0.0500 0.0014
## 6 0.0264 nan 0.0500 0.0006
## 7 0.0249 nan 0.0500 0.0006
## 8 0.0235 nan 0.0500 0.0010
## 9 0.0221 nan 0.0500 0.0008
## 10 0.0206 nan 0.0500 0.0010
## 20 0.0105 nan 0.0500 0.0005
## 40 0.0043 nan 0.0500 0.0002
## 60 0.0017 nan 0.0500 -0.0000
## 80 0.0008 nan 0.0500 0.0000
## 100 0.0003 nan 0.0500 0.0000
## 120 0.0001 nan 0.0500 0.0000
## 140 0.0001 nan 0.0500 -0.0000
## 160 0.0000 nan 0.0500 -0.0000
## 180 0.0000 nan 0.0500 0.0000
## 200 0.0000 nan 0.0500 0.0000
##
## - Fold25: shrinkage=0.05, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold25: shrinkage=0.05, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0368 nan 0.0500 0.0030
## 2 0.0337 nan 0.0500 0.0027
## 3 0.0316 nan 0.0500 0.0020
## 4 0.0291 nan 0.0500 0.0015
## 5 0.0279 nan 0.0500 0.0011
## 6 0.0256 nan 0.0500 0.0020
## 7 0.0242 nan 0.0500 0.0013
## 8 0.0229 nan 0.0500 0.0007
## 9 0.0218 nan 0.0500 0.0010
## 10 0.0202 nan 0.0500 0.0010
## 20 0.0121 nan 0.0500 0.0001
## 40 0.0060 nan 0.0500 -0.0001
## 60 0.0032 nan 0.0500 -0.0000
## 80 0.0018 nan 0.0500 -0.0000
## 100 0.0012 nan 0.0500 -0.0000
## 120 0.0007 nan 0.0500 -0.0000
## 140 0.0005 nan 0.0500 0.0000
## 160 0.0004 nan 0.0500 -0.0000
## 180 0.0003 nan 0.0500 -0.0000
## 200 0.0002 nan 0.0500 0.0000
##
## - Fold25: shrinkage=0.05, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold25: shrinkage=0.05, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0366 nan 0.0500 0.0026
## 2 0.0340 nan 0.0500 0.0024
## 3 0.0325 nan 0.0500 0.0005
## 4 0.0308 nan 0.0500 -0.0003
## 5 0.0289 nan 0.0500 0.0016
## 6 0.0273 nan 0.0500 0.0014
## 7 0.0266 nan 0.0500 -0.0008
## 8 0.0252 nan 0.0500 0.0015
## 9 0.0244 nan 0.0500 0.0006
## 10 0.0229 nan 0.0500 0.0010
## 20 0.0146 nan 0.0500 0.0005
## 40 0.0078 nan 0.0500 0.0001
## 60 0.0050 nan 0.0500 0.0001
## 80 0.0035 nan 0.0500 0.0001
## 100 0.0023 nan 0.0500 -0.0001
## 120 0.0019 nan 0.0500 0.0000
## 140 0.0013 nan 0.0500 -0.0000
## 160 0.0010 nan 0.0500 -0.0000
## 180 0.0008 nan 0.0500 -0.0000
## 200 0.0006 nan 0.0500 -0.0000
##
## - Fold25: shrinkage=0.05, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold25: shrinkage=0.05, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0373 nan 0.0500 0.0003
## 2 0.0342 nan 0.0500 0.0022
## 3 0.0314 nan 0.0500 0.0016
## 4 0.0294 nan 0.0500 0.0002
## 5 0.0279 nan 0.0500 0.0012
## 6 0.0266 nan 0.0500 0.0001
## 7 0.0257 nan 0.0500 -0.0001
## 8 0.0236 nan 0.0500 0.0021
## 9 0.0221 nan 0.0500 0.0004
## 10 0.0207 nan 0.0500 0.0001
## 20 0.0108 nan 0.0500 0.0000
## 40 0.0032 nan 0.0500 0.0001
## 60 0.0010 nan 0.0500 -0.0000
## 80 0.0004 nan 0.0500 -0.0000
## 100 0.0002 nan 0.0500 0.0000
## 120 0.0001 nan 0.0500 0.0000
## 140 0.0001 nan 0.0500 -0.0000
## 160 0.0000 nan 0.0500 -0.0000
## 180 0.0000 nan 0.0500 -0.0000
## 200 0.0000 nan 0.0500 -0.0000
##
## - Fold25: shrinkage=0.05, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold25: shrinkage=0.05, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0367 nan 0.0500 0.0016
## 2 0.0342 nan 0.0500 0.0026
## 3 0.0310 nan 0.0500 0.0018
## 4 0.0295 nan 0.0500 0.0007
## 5 0.0269 nan 0.0500 0.0012
## 6 0.0252 nan 0.0500 0.0001
## 7 0.0236 nan 0.0500 0.0013
## 8 0.0222 nan 0.0500 0.0014
## 9 0.0206 nan 0.0500 0.0011
## 10 0.0191 nan 0.0500 0.0013
## 20 0.0108 nan 0.0500 0.0005
## 40 0.0048 nan 0.0500 0.0002
## 60 0.0022 nan 0.0500 0.0001
## 80 0.0011 nan 0.0500 -0.0000
## 100 0.0007 nan 0.0500 -0.0000
## 120 0.0004 nan 0.0500 -0.0000
## 140 0.0002 nan 0.0500 -0.0000
## 160 0.0002 nan 0.0500 0.0000
## 180 0.0001 nan 0.0500 -0.0000
## 200 0.0001 nan 0.0500 0.0000
##
## - Fold25: shrinkage=0.05, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold25: shrinkage=0.05, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0377 nan 0.0500 0.0018
## 2 0.0358 nan 0.0500 0.0017
## 3 0.0340 nan 0.0500 0.0010
## 4 0.0329 nan 0.0500 0.0010
## 5 0.0312 nan 0.0500 0.0019
## 6 0.0291 nan 0.0500 0.0017
## 7 0.0276 nan 0.0500 0.0015
## 8 0.0270 nan 0.0500 -0.0001
## 9 0.0251 nan 0.0500 0.0016
## 10 0.0238 nan 0.0500 0.0005
## 20 0.0155 nan 0.0500 0.0007
## 40 0.0083 nan 0.0500 0.0001
## 60 0.0057 nan 0.0500 -0.0000
## 80 0.0039 nan 0.0500 -0.0001
## 100 0.0028 nan 0.0500 -0.0000
## 120 0.0023 nan 0.0500 -0.0000
## 140 0.0016 nan 0.0500 -0.0000
## 160 0.0012 nan 0.0500 0.0000
## 180 0.0009 nan 0.0500 -0.0000
## 200 0.0007 nan 0.0500 -0.0000
##
## - Fold25: shrinkage=0.05, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold25: shrinkage=0.10, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0369 nan 0.1000 0.0027
## 2 0.0362 nan 0.1000 -0.0015
## 3 0.0323 nan 0.1000 0.0041
## 4 0.0287 nan 0.1000 0.0038
## 5 0.0268 nan 0.1000 0.0021
## 6 0.0235 nan 0.1000 0.0017
## 7 0.0221 nan 0.1000 0.0016
## 8 0.0200 nan 0.1000 0.0018
## 9 0.0181 nan 0.1000 0.0014
## 10 0.0166 nan 0.1000 0.0006
## 20 0.0071 nan 0.1000 -0.0000
## 40 0.0024 nan 0.1000 0.0001
## 60 0.0010 nan 0.1000 0.0000
## 80 0.0004 nan 0.1000 -0.0000
## 100 0.0001 nan 0.1000 -0.0000
## 120 0.0001 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold25: shrinkage=0.10, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold25: shrinkage=0.10, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0348 nan 0.1000 0.0041
## 2 0.0317 nan 0.1000 0.0001
## 3 0.0282 nan 0.1000 0.0033
## 4 0.0250 nan 0.1000 0.0035
## 5 0.0224 nan 0.1000 0.0020
## 6 0.0212 nan 0.1000 0.0010
## 7 0.0184 nan 0.1000 0.0027
## 8 0.0163 nan 0.1000 0.0015
## 9 0.0148 nan 0.1000 0.0015
## 10 0.0136 nan 0.1000 0.0013
## 20 0.0056 nan 0.1000 -0.0002
## 40 0.0019 nan 0.1000 0.0001
## 60 0.0007 nan 0.1000 0.0000
## 80 0.0003 nan 0.1000 0.0000
## 100 0.0001 nan 0.1000 0.0000
## 120 0.0001 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold25: shrinkage=0.10, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold25: shrinkage=0.10, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0343 nan 0.1000 0.0044
## 2 0.0302 nan 0.1000 0.0025
## 3 0.0255 nan 0.1000 0.0035
## 4 0.0224 nan 0.1000 0.0023
## 5 0.0209 nan 0.1000 0.0010
## 6 0.0196 nan 0.1000 0.0009
## 7 0.0173 nan 0.1000 0.0022
## 8 0.0159 nan 0.1000 0.0009
## 9 0.0154 nan 0.1000 -0.0000
## 10 0.0141 nan 0.1000 0.0012
## 20 0.0091 nan 0.1000 0.0001
## 40 0.0039 nan 0.1000 -0.0001
## 60 0.0024 nan 0.1000 0.0000
## 80 0.0017 nan 0.1000 -0.0000
## 100 0.0011 nan 0.1000 0.0001
## 120 0.0007 nan 0.1000 -0.0000
## 140 0.0005 nan 0.1000 -0.0000
## 160 0.0003 nan 0.1000 -0.0000
## 180 0.0002 nan 0.1000 -0.0000
## 200 0.0001 nan 0.1000 -0.0000
##
## - Fold25: shrinkage=0.10, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold25: shrinkage=0.10, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0358 nan 0.1000 -0.0012
## 2 0.0317 nan 0.1000 0.0048
## 3 0.0288 nan 0.1000 0.0017
## 4 0.0261 nan 0.1000 0.0017
## 5 0.0223 nan 0.1000 0.0038
## 6 0.0193 nan 0.1000 0.0028
## 7 0.0171 nan 0.1000 0.0017
## 8 0.0148 nan 0.1000 0.0015
## 9 0.0133 nan 0.1000 0.0003
## 10 0.0118 nan 0.1000 0.0009
## 20 0.0040 nan 0.1000 0.0002
## 40 0.0007 nan 0.1000 0.0000
## 60 0.0002 nan 0.1000 -0.0000
## 80 0.0000 nan 0.1000 0.0000
## 100 0.0000 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold25: shrinkage=0.10, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold25: shrinkage=0.10, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0343 nan 0.1000 0.0015
## 2 0.0322 nan 0.1000 0.0000
## 3 0.0290 nan 0.1000 0.0021
## 4 0.0263 nan 0.1000 0.0005
## 5 0.0231 nan 0.1000 0.0012
## 6 0.0216 nan 0.1000 -0.0010
## 7 0.0197 nan 0.1000 0.0018
## 8 0.0167 nan 0.1000 0.0030
## 9 0.0152 nan 0.1000 0.0017
## 10 0.0141 nan 0.1000 0.0009
## 20 0.0067 nan 0.1000 0.0007
## 40 0.0023 nan 0.1000 0.0001
## 60 0.0011 nan 0.1000 -0.0001
## 80 0.0006 nan 0.1000 -0.0000
## 100 0.0003 nan 0.1000 -0.0000
## 120 0.0002 nan 0.1000 -0.0000
## 140 0.0001 nan 0.1000 0.0000
## 160 0.0001 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold25: shrinkage=0.10, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold25: shrinkage=0.10, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0357 nan 0.1000 0.0034
## 2 0.0318 nan 0.1000 0.0017
## 3 0.0282 nan 0.1000 0.0035
## 4 0.0248 nan 0.1000 0.0028
## 5 0.0222 nan 0.1000 0.0021
## 6 0.0197 nan 0.1000 0.0024
## 7 0.0181 nan 0.1000 0.0009
## 8 0.0167 nan 0.1000 -0.0003
## 9 0.0154 nan 0.1000 0.0015
## 10 0.0145 nan 0.1000 0.0003
## 20 0.0080 nan 0.1000 0.0000
## 40 0.0034 nan 0.1000 -0.0000
## 60 0.0015 nan 0.1000 0.0000
## 80 0.0008 nan 0.1000 0.0000
## 100 0.0005 nan 0.1000 -0.0000
## 120 0.0003 nan 0.1000 0.0000
## 140 0.0002 nan 0.1000 0.0000
## 160 0.0001 nan 0.1000 -0.0000
## 180 0.0001 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold25: shrinkage=0.10, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold25: shrinkage=0.10, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0355 nan 0.1000 0.0033
## 2 0.0305 nan 0.1000 0.0051
## 3 0.0260 nan 0.1000 0.0033
## 4 0.0227 nan 0.1000 0.0016
## 5 0.0190 nan 0.1000 0.0029
## 6 0.0159 nan 0.1000 0.0020
## 7 0.0136 nan 0.1000 0.0014
## 8 0.0119 nan 0.1000 0.0005
## 9 0.0106 nan 0.1000 0.0009
## 10 0.0092 nan 0.1000 0.0010
## 20 0.0037 nan 0.1000 -0.0000
## 40 0.0006 nan 0.1000 -0.0000
## 60 0.0001 nan 0.1000 0.0000
## 80 0.0000 nan 0.1000 0.0000
## 100 0.0000 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 0.0000
##
## - Fold25: shrinkage=0.10, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold25: shrinkage=0.10, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0361 nan 0.1000 0.0009
## 2 0.0309 nan 0.1000 0.0028
## 3 0.0275 nan 0.1000 0.0030
## 4 0.0238 nan 0.1000 0.0023
## 5 0.0211 nan 0.1000 0.0025
## 6 0.0174 nan 0.1000 0.0025
## 7 0.0157 nan 0.1000 0.0003
## 8 0.0131 nan 0.1000 0.0015
## 9 0.0116 nan 0.1000 0.0011
## 10 0.0104 nan 0.1000 0.0015
## 20 0.0041 nan 0.1000 0.0002
## 40 0.0011 nan 0.1000 -0.0001
## 60 0.0003 nan 0.1000 -0.0000
## 80 0.0001 nan 0.1000 -0.0000
## 100 0.0001 nan 0.1000 0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 0.0000
##
## - Fold25: shrinkage=0.10, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold25: shrinkage=0.10, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0369 nan 0.1000 0.0026
## 2 0.0321 nan 0.1000 0.0049
## 3 0.0277 nan 0.1000 0.0029
## 4 0.0242 nan 0.1000 0.0019
## 5 0.0213 nan 0.1000 0.0027
## 6 0.0182 nan 0.1000 0.0012
## 7 0.0164 nan 0.1000 0.0016
## 8 0.0156 nan 0.1000 0.0002
## 9 0.0146 nan 0.1000 0.0006
## 10 0.0135 nan 0.1000 0.0004
## 20 0.0080 nan 0.1000 -0.0000
## 40 0.0031 nan 0.1000 -0.0000
## 60 0.0018 nan 0.1000 0.0000
## 80 0.0011 nan 0.1000 -0.0000
## 100 0.0008 nan 0.1000 -0.0000
## 120 0.0005 nan 0.1000 -0.0000
## 140 0.0003 nan 0.1000 0.0000
## 160 0.0002 nan 0.1000 -0.0000
## 180 0.0002 nan 0.1000 0.0000
## 200 0.0001 nan 0.1000 0.0000
##
## - Fold25: shrinkage=0.10, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold26: shrinkage=0.01, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0437 nan 0.0100 -0.0001
## 2 0.0431 nan 0.0100 0.0005
## 3 0.0425 nan 0.0100 0.0006
## 4 0.0420 nan 0.0100 0.0004
## 5 0.0417 nan 0.0100 0.0002
## 6 0.0412 nan 0.0100 0.0004
## 7 0.0407 nan 0.0100 0.0006
## 8 0.0403 nan 0.0100 0.0001
## 9 0.0399 nan 0.0100 0.0004
## 10 0.0393 nan 0.0100 0.0005
## 20 0.0342 nan 0.0100 0.0007
## 40 0.0271 nan 0.0100 0.0003
## 60 0.0223 nan 0.0100 0.0002
## 80 0.0180 nan 0.0100 0.0000
## 100 0.0147 nan 0.0100 0.0001
## 120 0.0120 nan 0.0100 0.0001
## 140 0.0101 nan 0.0100 0.0001
## 160 0.0085 nan 0.0100 0.0001
## 180 0.0072 nan 0.0100 0.0000
## 200 0.0062 nan 0.0100 0.0000
##
## - Fold26: shrinkage=0.01, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold26: shrinkage=0.01, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0433 nan 0.0100 0.0005
## 2 0.0428 nan 0.0100 0.0004
## 3 0.0422 nan 0.0100 0.0006
## 4 0.0415 nan 0.0100 0.0006
## 5 0.0410 nan 0.0100 0.0004
## 6 0.0404 nan 0.0100 0.0002
## 7 0.0399 nan 0.0100 0.0006
## 8 0.0396 nan 0.0100 0.0002
## 9 0.0391 nan 0.0100 0.0004
## 10 0.0386 nan 0.0100 0.0005
## 20 0.0344 nan 0.0100 0.0002
## 40 0.0273 nan 0.0100 0.0001
## 60 0.0216 nan 0.0100 0.0002
## 80 0.0174 nan 0.0100 0.0002
## 100 0.0147 nan 0.0100 0.0000
## 120 0.0123 nan 0.0100 0.0001
## 140 0.0105 nan 0.0100 0.0000
## 160 0.0088 nan 0.0100 0.0000
## 180 0.0073 nan 0.0100 0.0000
## 200 0.0062 nan 0.0100 0.0000
##
## - Fold26: shrinkage=0.01, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold26: shrinkage=0.01, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0434 nan 0.0100 0.0005
## 2 0.0427 nan 0.0100 0.0005
## 3 0.0421 nan 0.0100 0.0005
## 4 0.0417 nan 0.0100 0.0003
## 5 0.0414 nan 0.0100 0.0003
## 6 0.0408 nan 0.0100 0.0006
## 7 0.0403 nan 0.0100 0.0004
## 8 0.0398 nan 0.0100 0.0005
## 9 0.0392 nan 0.0100 0.0005
## 10 0.0388 nan 0.0100 0.0004
## 20 0.0347 nan 0.0100 0.0003
## 40 0.0284 nan 0.0100 0.0003
## 60 0.0225 nan 0.0100 0.0002
## 80 0.0188 nan 0.0100 0.0002
## 100 0.0163 nan 0.0100 0.0000
## 120 0.0138 nan 0.0100 0.0000
## 140 0.0121 nan 0.0100 0.0001
## 160 0.0103 nan 0.0100 0.0000
## 180 0.0092 nan 0.0100 0.0001
## 200 0.0080 nan 0.0100 0.0000
##
## - Fold26: shrinkage=0.01, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold26: shrinkage=0.01, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0434 nan 0.0100 0.0002
## 2 0.0427 nan 0.0100 0.0006
## 3 0.0422 nan 0.0100 0.0001
## 4 0.0418 nan 0.0100 0.0002
## 5 0.0413 nan 0.0100 0.0005
## 6 0.0406 nan 0.0100 0.0007
## 7 0.0401 nan 0.0100 0.0004
## 8 0.0395 nan 0.0100 0.0004
## 9 0.0390 nan 0.0100 0.0004
## 10 0.0386 nan 0.0100 0.0001
## 20 0.0333 nan 0.0100 0.0002
## 40 0.0253 nan 0.0100 -0.0000
## 60 0.0196 nan 0.0100 0.0001
## 80 0.0155 nan 0.0100 0.0001
## 100 0.0121 nan 0.0100 0.0001
## 120 0.0095 nan 0.0100 0.0000
## 140 0.0079 nan 0.0100 0.0000
## 160 0.0064 nan 0.0100 -0.0000
## 180 0.0053 nan 0.0100 0.0000
## 200 0.0043 nan 0.0100 0.0000
##
## - Fold26: shrinkage=0.01, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold26: shrinkage=0.01, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0431 nan 0.0100 0.0004
## 2 0.0426 nan 0.0100 0.0004
## 3 0.0419 nan 0.0100 0.0008
## 4 0.0413 nan 0.0100 0.0004
## 5 0.0406 nan 0.0100 0.0005
## 6 0.0401 nan 0.0100 0.0005
## 7 0.0396 nan 0.0100 0.0006
## 8 0.0390 nan 0.0100 0.0005
## 9 0.0386 nan 0.0100 0.0000
## 10 0.0382 nan 0.0100 0.0003
## 20 0.0336 nan 0.0100 0.0003
## 40 0.0260 nan 0.0100 0.0003
## 60 0.0200 nan 0.0100 0.0003
## 80 0.0157 nan 0.0100 0.0002
## 100 0.0124 nan 0.0100 0.0001
## 120 0.0100 nan 0.0100 0.0001
## 140 0.0081 nan 0.0100 0.0001
## 160 0.0070 nan 0.0100 0.0000
## 180 0.0058 nan 0.0100 0.0000
## 200 0.0047 nan 0.0100 -0.0000
##
## - Fold26: shrinkage=0.01, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold26: shrinkage=0.01, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0433 nan 0.0100 0.0004
## 2 0.0429 nan 0.0100 0.0005
## 3 0.0425 nan 0.0100 0.0003
## 4 0.0420 nan 0.0100 0.0006
## 5 0.0413 nan 0.0100 0.0006
## 6 0.0408 nan 0.0100 0.0005
## 7 0.0402 nan 0.0100 0.0004
## 8 0.0396 nan 0.0100 0.0004
## 9 0.0391 nan 0.0100 0.0005
## 10 0.0387 nan 0.0100 0.0005
## 20 0.0343 nan 0.0100 0.0004
## 40 0.0278 nan 0.0100 0.0002
## 60 0.0228 nan 0.0100 0.0002
## 80 0.0190 nan 0.0100 -0.0000
## 100 0.0159 nan 0.0100 0.0001
## 120 0.0136 nan 0.0100 0.0000
## 140 0.0117 nan 0.0100 0.0001
## 160 0.0103 nan 0.0100 -0.0001
## 180 0.0090 nan 0.0100 0.0001
## 200 0.0079 nan 0.0100 -0.0000
##
## - Fold26: shrinkage=0.01, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold26: shrinkage=0.01, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0432 nan 0.0100 0.0006
## 2 0.0425 nan 0.0100 0.0007
## 3 0.0420 nan 0.0100 0.0003
## 4 0.0414 nan 0.0100 0.0007
## 5 0.0407 nan 0.0100 0.0007
## 6 0.0402 nan 0.0100 0.0004
## 7 0.0394 nan 0.0100 0.0005
## 8 0.0389 nan 0.0100 0.0002
## 9 0.0383 nan 0.0100 0.0005
## 10 0.0376 nan 0.0100 0.0007
## 20 0.0326 nan 0.0100 0.0003
## 40 0.0239 nan 0.0100 0.0004
## 60 0.0185 nan 0.0100 -0.0001
## 80 0.0142 nan 0.0100 0.0001
## 100 0.0110 nan 0.0100 0.0001
## 120 0.0085 nan 0.0100 0.0000
## 140 0.0069 nan 0.0100 0.0000
## 160 0.0054 nan 0.0100 0.0000
## 180 0.0042 nan 0.0100 -0.0000
## 200 0.0033 nan 0.0100 0.0000
##
## - Fold26: shrinkage=0.01, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold26: shrinkage=0.01, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0432 nan 0.0100 0.0006
## 2 0.0425 nan 0.0100 0.0006
## 3 0.0420 nan 0.0100 0.0004
## 4 0.0412 nan 0.0100 0.0005
## 5 0.0408 nan 0.0100 0.0001
## 6 0.0402 nan 0.0100 0.0006
## 7 0.0395 nan 0.0100 0.0007
## 8 0.0390 nan 0.0100 0.0003
## 9 0.0384 nan 0.0100 0.0004
## 10 0.0378 nan 0.0100 0.0004
## 20 0.0330 nan 0.0100 0.0005
## 40 0.0248 nan 0.0100 0.0002
## 60 0.0195 nan 0.0100 0.0002
## 80 0.0151 nan 0.0100 0.0001
## 100 0.0120 nan 0.0100 0.0001
## 120 0.0094 nan 0.0100 0.0001
## 140 0.0076 nan 0.0100 0.0000
## 160 0.0062 nan 0.0100 0.0000
## 180 0.0050 nan 0.0100 0.0000
## 200 0.0043 nan 0.0100 0.0000
##
## - Fold26: shrinkage=0.01, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold26: shrinkage=0.01, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0433 nan 0.0100 0.0004
## 2 0.0427 nan 0.0100 0.0006
## 3 0.0422 nan 0.0100 0.0004
## 4 0.0415 nan 0.0100 0.0005
## 5 0.0408 nan 0.0100 0.0006
## 6 0.0403 nan 0.0100 0.0005
## 7 0.0397 nan 0.0100 0.0001
## 8 0.0395 nan 0.0100 0.0003
## 9 0.0389 nan 0.0100 0.0005
## 10 0.0387 nan 0.0100 0.0001
## 20 0.0346 nan 0.0100 0.0000
## 40 0.0280 nan 0.0100 0.0001
## 60 0.0226 nan 0.0100 0.0003
## 80 0.0191 nan 0.0100 0.0001
## 100 0.0162 nan 0.0100 0.0001
## 120 0.0140 nan 0.0100 -0.0000
## 140 0.0121 nan 0.0100 0.0001
## 160 0.0107 nan 0.0100 0.0001
## 180 0.0095 nan 0.0100 0.0000
## 200 0.0085 nan 0.0100 0.0001
##
## - Fold26: shrinkage=0.01, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold26: shrinkage=0.05, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0407 nan 0.0500 0.0030
## 2 0.0385 nan 0.0500 0.0023
## 3 0.0359 nan 0.0500 0.0023
## 4 0.0340 nan 0.0500 0.0013
## 5 0.0318 nan 0.0500 0.0008
## 6 0.0305 nan 0.0500 0.0012
## 7 0.0287 nan 0.0500 0.0005
## 8 0.0270 nan 0.0500 0.0015
## 9 0.0255 nan 0.0500 0.0002
## 10 0.0237 nan 0.0500 0.0013
## 20 0.0134 nan 0.0500 0.0003
## 40 0.0056 nan 0.0500 0.0002
## 60 0.0028 nan 0.0500 -0.0000
## 80 0.0015 nan 0.0500 0.0000
## 100 0.0008 nan 0.0500 0.0000
## 120 0.0005 nan 0.0500 0.0000
## 140 0.0003 nan 0.0500 -0.0000
## 160 0.0002 nan 0.0500 0.0000
## 180 0.0001 nan 0.0500 0.0000
## 200 0.0001 nan 0.0500 0.0000
##
## - Fold26: shrinkage=0.05, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold26: shrinkage=0.05, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0407 nan 0.0500 0.0026
## 2 0.0383 nan 0.0500 0.0022
## 3 0.0365 nan 0.0500 0.0019
## 4 0.0349 nan 0.0500 0.0011
## 5 0.0339 nan 0.0500 -0.0000
## 6 0.0329 nan 0.0500 0.0008
## 7 0.0304 nan 0.0500 0.0017
## 8 0.0283 nan 0.0500 0.0016
## 9 0.0268 nan 0.0500 0.0011
## 10 0.0256 nan 0.0500 0.0001
## 20 0.0161 nan 0.0500 0.0002
## 40 0.0063 nan 0.0500 0.0000
## 60 0.0031 nan 0.0500 -0.0001
## 80 0.0018 nan 0.0500 0.0000
## 100 0.0011 nan 0.0500 -0.0000
## 120 0.0007 nan 0.0500 -0.0000
## 140 0.0005 nan 0.0500 -0.0000
## 160 0.0003 nan 0.0500 0.0000
## 180 0.0002 nan 0.0500 -0.0000
## 200 0.0001 nan 0.0500 -0.0000
##
## - Fold26: shrinkage=0.05, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold26: shrinkage=0.05, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0406 nan 0.0500 0.0025
## 2 0.0387 nan 0.0500 0.0014
## 3 0.0373 nan 0.0500 0.0003
## 4 0.0348 nan 0.0500 0.0020
## 5 0.0331 nan 0.0500 0.0013
## 6 0.0309 nan 0.0500 0.0022
## 7 0.0300 nan 0.0500 0.0008
## 8 0.0283 nan 0.0500 0.0007
## 9 0.0263 nan 0.0500 0.0016
## 10 0.0258 nan 0.0500 0.0001
## 20 0.0168 nan 0.0500 0.0008
## 40 0.0086 nan 0.0500 -0.0003
## 60 0.0053 nan 0.0500 0.0001
## 80 0.0035 nan 0.0500 0.0001
## 100 0.0025 nan 0.0500 0.0000
## 120 0.0016 nan 0.0500 -0.0000
## 140 0.0012 nan 0.0500 -0.0000
## 160 0.0008 nan 0.0500 0.0000
## 180 0.0006 nan 0.0500 -0.0000
## 200 0.0004 nan 0.0500 0.0000
##
## - Fold26: shrinkage=0.05, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold26: shrinkage=0.05, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0409 nan 0.0500 0.0028
## 2 0.0382 nan 0.0500 0.0013
## 3 0.0367 nan 0.0500 0.0011
## 4 0.0336 nan 0.0500 0.0018
## 5 0.0319 nan 0.0500 -0.0002
## 6 0.0303 nan 0.0500 0.0002
## 7 0.0289 nan 0.0500 0.0007
## 8 0.0265 nan 0.0500 0.0019
## 9 0.0250 nan 0.0500 0.0012
## 10 0.0238 nan 0.0500 0.0001
## 20 0.0126 nan 0.0500 0.0005
## 40 0.0045 nan 0.0500 -0.0000
## 60 0.0017 nan 0.0500 0.0000
## 80 0.0007 nan 0.0500 0.0000
## 100 0.0004 nan 0.0500 0.0000
## 120 0.0002 nan 0.0500 0.0000
## 140 0.0001 nan 0.0500 0.0000
## 160 0.0001 nan 0.0500 -0.0000
## 180 0.0000 nan 0.0500 0.0000
## 200 0.0000 nan 0.0500 -0.0000
##
## - Fold26: shrinkage=0.05, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold26: shrinkage=0.05, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0418 nan 0.0500 0.0005
## 2 0.0397 nan 0.0500 0.0017
## 3 0.0386 nan 0.0500 0.0009
## 4 0.0357 nan 0.0500 0.0021
## 5 0.0328 nan 0.0500 0.0026
## 6 0.0296 nan 0.0500 0.0017
## 7 0.0285 nan 0.0500 -0.0005
## 8 0.0265 nan 0.0500 0.0013
## 9 0.0253 nan 0.0500 0.0007
## 10 0.0243 nan 0.0500 0.0004
## 20 0.0141 nan 0.0500 0.0009
## 40 0.0046 nan 0.0500 0.0002
## 60 0.0022 nan 0.0500 0.0000
## 80 0.0011 nan 0.0500 -0.0000
## 100 0.0007 nan 0.0500 -0.0000
## 120 0.0004 nan 0.0500 -0.0000
## 140 0.0002 nan 0.0500 0.0000
## 160 0.0002 nan 0.0500 -0.0000
## 180 0.0001 nan 0.0500 0.0000
## 200 0.0001 nan 0.0500 -0.0000
##
## - Fold26: shrinkage=0.05, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold26: shrinkage=0.05, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0412 nan 0.0500 0.0026
## 2 0.0390 nan 0.0500 0.0024
## 3 0.0375 nan 0.0500 0.0017
## 4 0.0348 nan 0.0500 0.0025
## 5 0.0325 nan 0.0500 0.0021
## 6 0.0310 nan 0.0500 0.0012
## 7 0.0295 nan 0.0500 0.0015
## 8 0.0279 nan 0.0500 0.0009
## 9 0.0267 nan 0.0500 0.0007
## 10 0.0257 nan 0.0500 0.0008
## 20 0.0158 nan 0.0500 0.0007
## 40 0.0075 nan 0.0500 0.0002
## 60 0.0045 nan 0.0500 -0.0001
## 80 0.0031 nan 0.0500 -0.0000
## 100 0.0021 nan 0.0500 -0.0000
## 120 0.0015 nan 0.0500 0.0000
## 140 0.0011 nan 0.0500 0.0000
## 160 0.0008 nan 0.0500 -0.0000
## 180 0.0006 nan 0.0500 -0.0000
## 200 0.0004 nan 0.0500 -0.0000
##
## - Fold26: shrinkage=0.05, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold26: shrinkage=0.05, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0413 nan 0.0500 0.0016
## 2 0.0377 nan 0.0500 0.0027
## 3 0.0346 nan 0.0500 0.0029
## 4 0.0315 nan 0.0500 0.0016
## 5 0.0297 nan 0.0500 0.0000
## 6 0.0276 nan 0.0500 0.0004
## 7 0.0261 nan 0.0500 0.0009
## 8 0.0249 nan 0.0500 0.0009
## 9 0.0231 nan 0.0500 0.0019
## 10 0.0221 nan 0.0500 0.0006
## 20 0.0130 nan 0.0500 0.0006
## 40 0.0037 nan 0.0500 -0.0000
## 60 0.0013 nan 0.0500 0.0000
## 80 0.0005 nan 0.0500 -0.0000
## 100 0.0002 nan 0.0500 -0.0000
## 120 0.0001 nan 0.0500 -0.0000
## 140 0.0001 nan 0.0500 -0.0000
## 160 0.0000 nan 0.0500 -0.0000
## 180 0.0000 nan 0.0500 0.0000
## 200 0.0000 nan 0.0500 0.0000
##
## - Fold26: shrinkage=0.05, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold26: shrinkage=0.05, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0408 nan 0.0500 0.0011
## 2 0.0381 nan 0.0500 0.0015
## 3 0.0361 nan 0.0500 0.0008
## 4 0.0351 nan 0.0500 -0.0000
## 5 0.0328 nan 0.0500 0.0018
## 6 0.0304 nan 0.0500 0.0022
## 7 0.0288 nan 0.0500 0.0009
## 8 0.0275 nan 0.0500 0.0010
## 9 0.0262 nan 0.0500 0.0003
## 10 0.0245 nan 0.0500 0.0015
## 20 0.0121 nan 0.0500 0.0005
## 40 0.0041 nan 0.0500 -0.0000
## 60 0.0018 nan 0.0500 -0.0000
## 80 0.0009 nan 0.0500 0.0000
## 100 0.0005 nan 0.0500 -0.0000
## 120 0.0003 nan 0.0500 -0.0000
## 140 0.0002 nan 0.0500 -0.0000
## 160 0.0001 nan 0.0500 -0.0000
## 180 0.0001 nan 0.0500 -0.0000
## 200 0.0000 nan 0.0500 -0.0000
##
## - Fold26: shrinkage=0.05, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold26: shrinkage=0.05, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0431 nan 0.0500 -0.0009
## 2 0.0412 nan 0.0500 0.0024
## 3 0.0386 nan 0.0500 0.0024
## 4 0.0368 nan 0.0500 0.0013
## 5 0.0346 nan 0.0500 0.0020
## 6 0.0330 nan 0.0500 0.0017
## 7 0.0321 nan 0.0500 -0.0012
## 8 0.0315 nan 0.0500 -0.0000
## 9 0.0294 nan 0.0500 0.0016
## 10 0.0276 nan 0.0500 0.0013
## 20 0.0175 nan 0.0500 0.0003
## 40 0.0085 nan 0.0500 0.0002
## 60 0.0047 nan 0.0500 0.0001
## 80 0.0029 nan 0.0500 -0.0000
## 100 0.0019 nan 0.0500 -0.0000
## 120 0.0015 nan 0.0500 0.0000
## 140 0.0010 nan 0.0500 0.0000
## 160 0.0007 nan 0.0500 -0.0000
## 180 0.0005 nan 0.0500 -0.0000
## 200 0.0004 nan 0.0500 -0.0000
##
## - Fold26: shrinkage=0.05, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold26: shrinkage=0.10, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0368 nan 0.1000 0.0054
## 2 0.0323 nan 0.1000 0.0002
## 3 0.0291 nan 0.1000 0.0017
## 4 0.0268 nan 0.1000 0.0015
## 5 0.0238 nan 0.1000 0.0033
## 6 0.0214 nan 0.1000 0.0015
## 7 0.0190 nan 0.1000 0.0013
## 8 0.0167 nan 0.1000 0.0007
## 9 0.0152 nan 0.1000 0.0007
## 10 0.0135 nan 0.1000 0.0009
## 20 0.0053 nan 0.1000 0.0000
## 40 0.0015 nan 0.1000 -0.0001
## 60 0.0005 nan 0.1000 0.0000
## 80 0.0002 nan 0.1000 -0.0000
## 100 0.0001 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 0.0000
##
## - Fold26: shrinkage=0.10, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold26: shrinkage=0.10, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0399 nan 0.1000 0.0021
## 2 0.0346 nan 0.1000 0.0053
## 3 0.0323 nan 0.1000 0.0020
## 4 0.0288 nan 0.1000 0.0037
## 5 0.0247 nan 0.1000 0.0036
## 6 0.0231 nan 0.1000 0.0014
## 7 0.0215 nan 0.1000 0.0011
## 8 0.0189 nan 0.1000 0.0023
## 9 0.0167 nan 0.1000 0.0018
## 10 0.0148 nan 0.1000 0.0015
## 20 0.0059 nan 0.1000 0.0002
## 40 0.0016 nan 0.1000 0.0000
## 60 0.0008 nan 0.1000 0.0000
## 80 0.0003 nan 0.1000 -0.0000
## 100 0.0002 nan 0.1000 -0.0000
## 120 0.0001 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold26: shrinkage=0.10, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold26: shrinkage=0.10, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0386 nan 0.1000 0.0047
## 2 0.0356 nan 0.1000 0.0024
## 3 0.0327 nan 0.1000 0.0011
## 4 0.0287 nan 0.1000 0.0027
## 5 0.0255 nan 0.1000 0.0034
## 6 0.0227 nan 0.1000 0.0017
## 7 0.0213 nan 0.1000 0.0008
## 8 0.0187 nan 0.1000 0.0015
## 9 0.0168 nan 0.1000 0.0021
## 10 0.0156 nan 0.1000 0.0016
## 20 0.0083 nan 0.1000 -0.0002
## 40 0.0033 nan 0.1000 -0.0000
## 60 0.0015 nan 0.1000 -0.0000
## 80 0.0008 nan 0.1000 0.0000
## 100 0.0005 nan 0.1000 -0.0000
## 120 0.0003 nan 0.1000 -0.0000
## 140 0.0002 nan 0.1000 -0.0000
## 160 0.0001 nan 0.1000 -0.0000
## 180 0.0001 nan 0.1000 0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold26: shrinkage=0.10, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold26: shrinkage=0.10, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0403 nan 0.1000 0.0009
## 2 0.0333 nan 0.1000 0.0053
## 3 0.0277 nan 0.1000 0.0049
## 4 0.0260 nan 0.1000 -0.0010
## 5 0.0215 nan 0.1000 0.0042
## 6 0.0180 nan 0.1000 0.0034
## 7 0.0156 nan 0.1000 0.0012
## 8 0.0128 nan 0.1000 0.0021
## 9 0.0108 nan 0.1000 0.0014
## 10 0.0100 nan 0.1000 0.0008
## 20 0.0030 nan 0.1000 -0.0000
## 40 0.0007 nan 0.1000 -0.0000
## 60 0.0003 nan 0.1000 0.0000
## 80 0.0001 nan 0.1000 -0.0000
## 100 0.0000 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 0.0000
## 180 0.0000 nan 0.1000 0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold26: shrinkage=0.10, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold26: shrinkage=0.10, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0402 nan 0.1000 0.0005
## 2 0.0361 nan 0.1000 0.0029
## 3 0.0307 nan 0.1000 0.0047
## 4 0.0263 nan 0.1000 0.0028
## 5 0.0223 nan 0.1000 0.0031
## 6 0.0201 nan 0.1000 -0.0002
## 7 0.0194 nan 0.1000 -0.0002
## 8 0.0171 nan 0.1000 0.0011
## 9 0.0146 nan 0.1000 0.0023
## 10 0.0136 nan 0.1000 0.0005
## 20 0.0043 nan 0.1000 0.0003
## 40 0.0011 nan 0.1000 0.0000
## 60 0.0005 nan 0.1000 -0.0000
## 80 0.0002 nan 0.1000 -0.0000
## 100 0.0001 nan 0.1000 0.0000
## 120 0.0001 nan 0.1000 -0.0000
## 140 0.0001 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold26: shrinkage=0.10, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold26: shrinkage=0.10, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0405 nan 0.1000 0.0030
## 2 0.0360 nan 0.1000 0.0026
## 3 0.0315 nan 0.1000 0.0039
## 4 0.0274 nan 0.1000 0.0029
## 5 0.0234 nan 0.1000 0.0026
## 6 0.0207 nan 0.1000 0.0022
## 7 0.0184 nan 0.1000 0.0018
## 8 0.0178 nan 0.1000 0.0004
## 9 0.0168 nan 0.1000 0.0008
## 10 0.0156 nan 0.1000 0.0002
## 20 0.0080 nan 0.1000 0.0001
## 40 0.0032 nan 0.1000 -0.0002
## 60 0.0022 nan 0.1000 -0.0002
## 80 0.0011 nan 0.1000 -0.0000
## 100 0.0006 nan 0.1000 -0.0000
## 120 0.0003 nan 0.1000 -0.0000
## 140 0.0002 nan 0.1000 -0.0000
## 160 0.0002 nan 0.1000 -0.0000
## 180 0.0001 nan 0.1000 -0.0000
## 200 0.0001 nan 0.1000 -0.0000
##
## - Fold26: shrinkage=0.10, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold26: shrinkage=0.10, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0387 nan 0.1000 0.0031
## 2 0.0352 nan 0.1000 -0.0004
## 3 0.0306 nan 0.1000 0.0026
## 4 0.0265 nan 0.1000 0.0026
## 5 0.0234 nan 0.1000 0.0035
## 6 0.0204 nan 0.1000 0.0019
## 7 0.0180 nan 0.1000 0.0015
## 8 0.0151 nan 0.1000 0.0016
## 9 0.0132 nan 0.1000 0.0008
## 10 0.0113 nan 0.1000 0.0010
## 20 0.0040 nan 0.1000 0.0005
## 40 0.0004 nan 0.1000 -0.0000
## 60 0.0001 nan 0.1000 -0.0000
## 80 0.0000 nan 0.1000 -0.0000
## 100 0.0000 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold26: shrinkage=0.10, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold26: shrinkage=0.10, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0392 nan 0.1000 0.0024
## 2 0.0348 nan 0.1000 0.0023
## 3 0.0289 nan 0.1000 0.0048
## 4 0.0245 nan 0.1000 0.0030
## 5 0.0216 nan 0.1000 0.0027
## 6 0.0183 nan 0.1000 0.0017
## 7 0.0158 nan 0.1000 0.0007
## 8 0.0139 nan 0.1000 -0.0006
## 9 0.0122 nan 0.1000 0.0009
## 10 0.0110 nan 0.1000 0.0012
## 20 0.0040 nan 0.1000 -0.0003
## 40 0.0009 nan 0.1000 -0.0000
## 60 0.0004 nan 0.1000 -0.0000
## 80 0.0003 nan 0.1000 -0.0000
## 100 0.0001 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold26: shrinkage=0.10, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold26: shrinkage=0.10, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0375 nan 0.1000 0.0051
## 2 0.0333 nan 0.1000 0.0036
## 3 0.0289 nan 0.1000 0.0037
## 4 0.0268 nan 0.1000 0.0020
## 5 0.0251 nan 0.1000 0.0008
## 6 0.0231 nan 0.1000 0.0003
## 7 0.0210 nan 0.1000 0.0020
## 8 0.0199 nan 0.1000 0.0009
## 9 0.0188 nan 0.1000 0.0011
## 10 0.0177 nan 0.1000 0.0009
## 20 0.0091 nan 0.1000 0.0001
## 40 0.0033 nan 0.1000 -0.0000
## 60 0.0015 nan 0.1000 0.0000
## 80 0.0008 nan 0.1000 0.0000
## 100 0.0005 nan 0.1000 -0.0000
## 120 0.0002 nan 0.1000 -0.0000
## 140 0.0001 nan 0.1000 -0.0000
## 160 0.0001 nan 0.1000 -0.0000
## 180 0.0001 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold26: shrinkage=0.10, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold27: shrinkage=0.01, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0436 nan 0.0100 0.0007
## 2 0.0428 nan 0.0100 0.0006
## 3 0.0423 nan 0.0100 0.0002
## 4 0.0416 nan 0.0100 0.0005
## 5 0.0409 nan 0.0100 0.0004
## 6 0.0405 nan 0.0100 0.0002
## 7 0.0401 nan 0.0100 0.0001
## 8 0.0395 nan 0.0100 0.0006
## 9 0.0391 nan 0.0100 0.0001
## 10 0.0387 nan 0.0100 0.0004
## 20 0.0344 nan 0.0100 -0.0000
## 40 0.0274 nan 0.0100 0.0001
## 60 0.0225 nan 0.0100 0.0001
## 80 0.0187 nan 0.0100 0.0001
## 100 0.0152 nan 0.0100 -0.0000
## 120 0.0128 nan 0.0100 0.0001
## 140 0.0109 nan 0.0100 0.0000
## 160 0.0091 nan 0.0100 -0.0000
## 180 0.0076 nan 0.0100 0.0001
## 200 0.0065 nan 0.0100 0.0000
##
## - Fold27: shrinkage=0.01, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold27: shrinkage=0.01, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0436 nan 0.0100 0.0002
## 2 0.0431 nan 0.0100 0.0005
## 3 0.0427 nan 0.0100 0.0002
## 4 0.0422 nan 0.0100 0.0004
## 5 0.0417 nan 0.0100 0.0003
## 6 0.0412 nan 0.0100 0.0006
## 7 0.0405 nan 0.0100 0.0004
## 8 0.0403 nan 0.0100 0.0002
## 9 0.0398 nan 0.0100 0.0003
## 10 0.0393 nan 0.0100 0.0004
## 20 0.0351 nan 0.0100 0.0002
## 40 0.0281 nan 0.0100 0.0004
## 60 0.0225 nan 0.0100 0.0003
## 80 0.0182 nan 0.0100 0.0001
## 100 0.0152 nan 0.0100 0.0002
## 120 0.0125 nan 0.0100 0.0001
## 140 0.0105 nan 0.0100 0.0000
## 160 0.0089 nan 0.0100 0.0000
## 180 0.0076 nan 0.0100 0.0001
## 200 0.0065 nan 0.0100 0.0001
##
## - Fold27: shrinkage=0.01, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold27: shrinkage=0.01, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0438 nan 0.0100 0.0004
## 2 0.0431 nan 0.0100 0.0006
## 3 0.0425 nan 0.0100 0.0004
## 4 0.0420 nan 0.0100 0.0006
## 5 0.0415 nan 0.0100 0.0003
## 6 0.0411 nan 0.0100 0.0003
## 7 0.0406 nan 0.0100 0.0002
## 8 0.0401 nan 0.0100 0.0005
## 9 0.0398 nan 0.0100 0.0001
## 10 0.0393 nan 0.0100 0.0005
## 20 0.0345 nan 0.0100 0.0004
## 40 0.0279 nan 0.0100 -0.0000
## 60 0.0224 nan 0.0100 0.0001
## 80 0.0185 nan 0.0100 -0.0000
## 100 0.0156 nan 0.0100 0.0000
## 120 0.0132 nan 0.0100 0.0001
## 140 0.0114 nan 0.0100 0.0000
## 160 0.0101 nan 0.0100 0.0000
## 180 0.0086 nan 0.0100 0.0000
## 200 0.0076 nan 0.0100 -0.0000
##
## - Fold27: shrinkage=0.01, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold27: shrinkage=0.01, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0437 nan 0.0100 0.0007
## 2 0.0427 nan 0.0100 0.0006
## 3 0.0422 nan 0.0100 0.0004
## 4 0.0416 nan 0.0100 0.0005
## 5 0.0410 nan 0.0100 0.0005
## 6 0.0406 nan 0.0100 0.0003
## 7 0.0401 nan 0.0100 0.0000
## 8 0.0395 nan 0.0100 0.0005
## 9 0.0390 nan 0.0100 0.0004
## 10 0.0383 nan 0.0100 0.0006
## 20 0.0334 nan 0.0100 -0.0000
## 40 0.0253 nan 0.0100 0.0002
## 60 0.0193 nan 0.0100 0.0003
## 80 0.0153 nan 0.0100 0.0002
## 100 0.0122 nan 0.0100 -0.0000
## 120 0.0096 nan 0.0100 0.0000
## 140 0.0077 nan 0.0100 0.0000
## 160 0.0062 nan 0.0100 0.0000
## 180 0.0050 nan 0.0100 0.0001
## 200 0.0039 nan 0.0100 -0.0000
##
## - Fold27: shrinkage=0.01, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold27: shrinkage=0.01, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0435 nan 0.0100 0.0007
## 2 0.0431 nan 0.0100 0.0001
## 3 0.0425 nan 0.0100 0.0005
## 4 0.0419 nan 0.0100 0.0004
## 5 0.0413 nan 0.0100 0.0006
## 6 0.0405 nan 0.0100 0.0005
## 7 0.0401 nan 0.0100 0.0001
## 8 0.0397 nan 0.0100 0.0003
## 9 0.0391 nan 0.0100 0.0004
## 10 0.0387 nan 0.0100 0.0003
## 20 0.0339 nan 0.0100 0.0002
## 40 0.0256 nan 0.0100 0.0004
## 60 0.0199 nan 0.0100 0.0002
## 80 0.0155 nan 0.0100 0.0002
## 100 0.0125 nan 0.0100 0.0001
## 120 0.0097 nan 0.0100 0.0001
## 140 0.0081 nan 0.0100 -0.0000
## 160 0.0064 nan 0.0100 0.0001
## 180 0.0053 nan 0.0100 0.0000
## 200 0.0044 nan 0.0100 0.0000
##
## - Fold27: shrinkage=0.01, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold27: shrinkage=0.01, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0439 nan 0.0100 -0.0000
## 2 0.0432 nan 0.0100 0.0006
## 3 0.0426 nan 0.0100 0.0005
## 4 0.0423 nan 0.0100 0.0003
## 5 0.0419 nan 0.0100 0.0004
## 6 0.0417 nan 0.0100 -0.0001
## 7 0.0412 nan 0.0100 0.0004
## 8 0.0410 nan 0.0100 -0.0000
## 9 0.0404 nan 0.0100 0.0003
## 10 0.0399 nan 0.0100 0.0003
## 20 0.0350 nan 0.0100 0.0005
## 40 0.0293 nan 0.0100 0.0003
## 60 0.0242 nan 0.0100 0.0001
## 80 0.0199 nan 0.0100 0.0001
## 100 0.0166 nan 0.0100 0.0001
## 120 0.0141 nan 0.0100 0.0000
## 140 0.0117 nan 0.0100 0.0000
## 160 0.0101 nan 0.0100 0.0000
## 180 0.0093 nan 0.0100 0.0000
## 200 0.0085 nan 0.0100 -0.0000
##
## - Fold27: shrinkage=0.01, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold27: shrinkage=0.01, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0436 nan 0.0100 0.0004
## 2 0.0430 nan 0.0100 0.0005
## 3 0.0424 nan 0.0100 0.0001
## 4 0.0418 nan 0.0100 0.0004
## 5 0.0414 nan 0.0100 0.0002
## 6 0.0406 nan 0.0100 0.0007
## 7 0.0402 nan 0.0100 0.0003
## 8 0.0396 nan 0.0100 0.0006
## 9 0.0388 nan 0.0100 0.0007
## 10 0.0382 nan 0.0100 0.0004
## 20 0.0329 nan 0.0100 0.0005
## 40 0.0248 nan 0.0100 0.0003
## 60 0.0188 nan 0.0100 0.0002
## 80 0.0141 nan 0.0100 0.0001
## 100 0.0108 nan 0.0100 -0.0000
## 120 0.0084 nan 0.0100 0.0001
## 140 0.0064 nan 0.0100 0.0001
## 160 0.0052 nan 0.0100 -0.0000
## 180 0.0040 nan 0.0100 0.0000
## 200 0.0033 nan 0.0100 0.0000
##
## - Fold27: shrinkage=0.01, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold27: shrinkage=0.01, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0436 nan 0.0100 0.0004
## 2 0.0430 nan 0.0100 0.0005
## 3 0.0423 nan 0.0100 0.0006
## 4 0.0419 nan 0.0100 0.0002
## 5 0.0413 nan 0.0100 0.0005
## 6 0.0407 nan 0.0100 0.0005
## 7 0.0400 nan 0.0100 0.0008
## 8 0.0395 nan 0.0100 0.0005
## 9 0.0389 nan 0.0100 0.0004
## 10 0.0383 nan 0.0100 0.0005
## 20 0.0333 nan 0.0100 0.0005
## 40 0.0249 nan 0.0100 0.0002
## 60 0.0195 nan 0.0100 0.0003
## 80 0.0149 nan 0.0100 0.0002
## 100 0.0117 nan 0.0100 -0.0000
## 120 0.0092 nan 0.0100 0.0001
## 140 0.0076 nan 0.0100 0.0000
## 160 0.0063 nan 0.0100 0.0000
## 180 0.0051 nan 0.0100 0.0000
## 200 0.0043 nan 0.0100 0.0000
##
## - Fold27: shrinkage=0.01, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold27: shrinkage=0.01, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0438 nan 0.0100 0.0006
## 2 0.0432 nan 0.0100 0.0003
## 3 0.0426 nan 0.0100 0.0005
## 4 0.0421 nan 0.0100 0.0003
## 5 0.0416 nan 0.0100 0.0002
## 6 0.0412 nan 0.0100 0.0004
## 7 0.0408 nan 0.0100 0.0003
## 8 0.0403 nan 0.0100 0.0002
## 9 0.0400 nan 0.0100 0.0000
## 10 0.0396 nan 0.0100 0.0004
## 20 0.0353 nan 0.0100 0.0005
## 40 0.0283 nan 0.0100 0.0004
## 60 0.0225 nan 0.0100 0.0003
## 80 0.0192 nan 0.0100 0.0001
## 100 0.0161 nan 0.0100 0.0001
## 120 0.0139 nan 0.0100 0.0000
## 140 0.0122 nan 0.0100 0.0000
## 160 0.0107 nan 0.0100 0.0000
## 180 0.0093 nan 0.0100 0.0000
## 200 0.0084 nan 0.0100 0.0000
##
## - Fold27: shrinkage=0.01, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold27: shrinkage=0.05, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0421 nan 0.0500 0.0007
## 2 0.0398 nan 0.0500 0.0019
## 3 0.0371 nan 0.0500 0.0023
## 4 0.0348 nan 0.0500 0.0024
## 5 0.0325 nan 0.0500 0.0015
## 6 0.0304 nan 0.0500 0.0003
## 7 0.0286 nan 0.0500 0.0017
## 8 0.0264 nan 0.0500 0.0017
## 9 0.0248 nan 0.0500 0.0013
## 10 0.0232 nan 0.0500 0.0013
## 20 0.0141 nan 0.0500 0.0001
## 40 0.0053 nan 0.0500 0.0002
## 60 0.0025 nan 0.0500 0.0001
## 80 0.0014 nan 0.0500 -0.0000
## 100 0.0009 nan 0.0500 -0.0000
## 120 0.0006 nan 0.0500 -0.0000
## 140 0.0003 nan 0.0500 0.0000
## 160 0.0002 nan 0.0500 -0.0000
## 180 0.0001 nan 0.0500 -0.0000
## 200 0.0001 nan 0.0500 -0.0000
##
## - Fold27: shrinkage=0.05, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold27: shrinkage=0.05, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0412 nan 0.0500 0.0029
## 2 0.0385 nan 0.0500 0.0023
## 3 0.0353 nan 0.0500 0.0026
## 4 0.0329 nan 0.0500 0.0013
## 5 0.0311 nan 0.0500 0.0018
## 6 0.0290 nan 0.0500 0.0020
## 7 0.0270 nan 0.0500 0.0016
## 8 0.0250 nan 0.0500 0.0016
## 9 0.0240 nan 0.0500 0.0006
## 10 0.0228 nan 0.0500 0.0007
## 20 0.0150 nan 0.0500 -0.0002
## 40 0.0064 nan 0.0500 0.0002
## 60 0.0032 nan 0.0500 0.0001
## 80 0.0020 nan 0.0500 0.0000
## 100 0.0012 nan 0.0500 -0.0000
## 120 0.0008 nan 0.0500 0.0000
## 140 0.0005 nan 0.0500 0.0000
## 160 0.0004 nan 0.0500 0.0000
## 180 0.0003 nan 0.0500 0.0000
## 200 0.0002 nan 0.0500 -0.0000
##
## - Fold27: shrinkage=0.05, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold27: shrinkage=0.05, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0409 nan 0.0500 0.0027
## 2 0.0388 nan 0.0500 0.0009
## 3 0.0356 nan 0.0500 0.0021
## 4 0.0331 nan 0.0500 0.0023
## 5 0.0314 nan 0.0500 0.0012
## 6 0.0299 nan 0.0500 0.0018
## 7 0.0286 nan 0.0500 0.0014
## 8 0.0267 nan 0.0500 0.0015
## 9 0.0257 nan 0.0500 -0.0001
## 10 0.0246 nan 0.0500 0.0009
## 20 0.0156 nan 0.0500 -0.0001
## 40 0.0082 nan 0.0500 0.0002
## 60 0.0054 nan 0.0500 0.0000
## 80 0.0035 nan 0.0500 -0.0000
## 100 0.0026 nan 0.0500 -0.0000
## 120 0.0018 nan 0.0500 -0.0000
## 140 0.0012 nan 0.0500 0.0000
## 160 0.0008 nan 0.0500 0.0000
## 180 0.0006 nan 0.0500 -0.0000
## 200 0.0005 nan 0.0500 -0.0000
##
## - Fold27: shrinkage=0.05, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold27: shrinkage=0.05, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0421 nan 0.0500 0.0006
## 2 0.0399 nan 0.0500 0.0011
## 3 0.0366 nan 0.0500 0.0012
## 4 0.0339 nan 0.0500 0.0021
## 5 0.0320 nan 0.0500 0.0017
## 6 0.0288 nan 0.0500 0.0029
## 7 0.0278 nan 0.0500 0.0007
## 8 0.0255 nan 0.0500 0.0013
## 9 0.0244 nan 0.0500 0.0004
## 10 0.0227 nan 0.0500 0.0006
## 20 0.0119 nan 0.0500 0.0004
## 40 0.0041 nan 0.0500 0.0001
## 60 0.0016 nan 0.0500 0.0001
## 80 0.0007 nan 0.0500 -0.0000
## 100 0.0003 nan 0.0500 0.0000
## 120 0.0002 nan 0.0500 -0.0000
## 140 0.0001 nan 0.0500 -0.0000
## 160 0.0000 nan 0.0500 0.0000
## 180 0.0000 nan 0.0500 0.0000
## 200 0.0000 nan 0.0500 -0.0000
##
## - Fold27: shrinkage=0.05, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold27: shrinkage=0.05, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0411 nan 0.0500 0.0034
## 2 0.0380 nan 0.0500 0.0008
## 3 0.0357 nan 0.0500 0.0016
## 4 0.0336 nan 0.0500 0.0006
## 5 0.0312 nan 0.0500 0.0021
## 6 0.0289 nan 0.0500 0.0008
## 7 0.0264 nan 0.0500 0.0015
## 8 0.0246 nan 0.0500 0.0018
## 9 0.0229 nan 0.0500 0.0012
## 10 0.0224 nan 0.0500 -0.0004
## 20 0.0129 nan 0.0500 0.0003
## 40 0.0050 nan 0.0500 0.0001
## 60 0.0019 nan 0.0500 0.0001
## 80 0.0008 nan 0.0500 -0.0000
## 100 0.0005 nan 0.0500 0.0000
## 120 0.0003 nan 0.0500 0.0000
## 140 0.0002 nan 0.0500 -0.0000
## 160 0.0001 nan 0.0500 -0.0000
## 180 0.0001 nan 0.0500 -0.0000
## 200 0.0000 nan 0.0500 -0.0000
##
## - Fold27: shrinkage=0.05, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold27: shrinkage=0.05, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0410 nan 0.0500 0.0023
## 2 0.0392 nan 0.0500 0.0016
## 3 0.0366 nan 0.0500 0.0021
## 4 0.0348 nan 0.0500 0.0019
## 5 0.0329 nan 0.0500 0.0021
## 6 0.0313 nan 0.0500 0.0013
## 7 0.0296 nan 0.0500 0.0010
## 8 0.0287 nan 0.0500 0.0009
## 9 0.0273 nan 0.0500 0.0014
## 10 0.0263 nan 0.0500 0.0004
## 20 0.0150 nan 0.0500 0.0005
## 40 0.0072 nan 0.0500 0.0002
## 60 0.0042 nan 0.0500 0.0001
## 80 0.0026 nan 0.0500 0.0001
## 100 0.0019 nan 0.0500 0.0000
## 120 0.0013 nan 0.0500 -0.0000
## 140 0.0009 nan 0.0500 0.0000
## 160 0.0007 nan 0.0500 0.0000
## 180 0.0005 nan 0.0500 -0.0000
## 200 0.0004 nan 0.0500 0.0000
##
## - Fold27: shrinkage=0.05, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold27: shrinkage=0.05, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0411 nan 0.0500 0.0017
## 2 0.0391 nan 0.0500 -0.0000
## 3 0.0369 nan 0.0500 0.0014
## 4 0.0345 nan 0.0500 0.0020
## 5 0.0317 nan 0.0500 0.0011
## 6 0.0303 nan 0.0500 0.0011
## 7 0.0281 nan 0.0500 0.0015
## 8 0.0265 nan 0.0500 0.0019
## 9 0.0242 nan 0.0500 0.0022
## 10 0.0227 nan 0.0500 0.0009
## 20 0.0116 nan 0.0500 0.0002
## 40 0.0031 nan 0.0500 0.0001
## 60 0.0012 nan 0.0500 -0.0000
## 80 0.0005 nan 0.0500 0.0000
## 100 0.0002 nan 0.0500 -0.0000
## 120 0.0001 nan 0.0500 0.0000
## 140 0.0001 nan 0.0500 0.0000
## 160 0.0000 nan 0.0500 -0.0000
## 180 0.0000 nan 0.0500 -0.0000
## 200 0.0000 nan 0.0500 -0.0000
##
## - Fold27: shrinkage=0.05, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold27: shrinkage=0.05, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0409 nan 0.0500 0.0029
## 2 0.0385 nan 0.0500 0.0022
## 3 0.0363 nan 0.0500 0.0006
## 4 0.0342 nan 0.0500 0.0018
## 5 0.0307 nan 0.0500 0.0022
## 6 0.0285 nan 0.0500 0.0014
## 7 0.0266 nan 0.0500 0.0021
## 8 0.0251 nan 0.0500 0.0015
## 9 0.0239 nan 0.0500 0.0008
## 10 0.0230 nan 0.0500 0.0000
## 20 0.0113 nan 0.0500 0.0007
## 40 0.0036 nan 0.0500 0.0001
## 60 0.0016 nan 0.0500 -0.0000
## 80 0.0010 nan 0.0500 0.0000
## 100 0.0005 nan 0.0500 0.0000
## 120 0.0003 nan 0.0500 0.0000
## 140 0.0002 nan 0.0500 -0.0000
## 160 0.0002 nan 0.0500 0.0000
## 180 0.0001 nan 0.0500 -0.0000
## 200 0.0001 nan 0.0500 -0.0000
##
## - Fold27: shrinkage=0.05, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold27: shrinkage=0.05, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0414 nan 0.0500 0.0011
## 2 0.0390 nan 0.0500 0.0009
## 3 0.0364 nan 0.0500 0.0026
## 4 0.0345 nan 0.0500 0.0005
## 5 0.0334 nan 0.0500 0.0000
## 6 0.0311 nan 0.0500 0.0021
## 7 0.0300 nan 0.0500 0.0011
## 8 0.0288 nan 0.0500 0.0002
## 9 0.0273 nan 0.0500 0.0016
## 10 0.0268 nan 0.0500 -0.0003
## 20 0.0165 nan 0.0500 0.0008
## 40 0.0094 nan 0.0500 0.0000
## 60 0.0060 nan 0.0500 0.0002
## 80 0.0036 nan 0.0500 0.0000
## 100 0.0023 nan 0.0500 0.0000
## 120 0.0017 nan 0.0500 -0.0001
## 140 0.0012 nan 0.0500 0.0000
## 160 0.0007 nan 0.0500 -0.0000
## 180 0.0005 nan 0.0500 -0.0000
## 200 0.0004 nan 0.0500 -0.0000
##
## - Fold27: shrinkage=0.05, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold27: shrinkage=0.10, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0413 nan 0.1000 0.0032
## 2 0.0398 nan 0.1000 -0.0010
## 3 0.0368 nan 0.1000 0.0003
## 4 0.0335 nan 0.1000 0.0027
## 5 0.0298 nan 0.1000 0.0032
## 6 0.0266 nan 0.1000 0.0029
## 7 0.0247 nan 0.1000 0.0008
## 8 0.0219 nan 0.1000 0.0025
## 9 0.0196 nan 0.1000 0.0002
## 10 0.0171 nan 0.1000 0.0020
## 20 0.0085 nan 0.1000 0.0007
## 40 0.0022 nan 0.1000 -0.0000
## 60 0.0007 nan 0.1000 -0.0000
## 80 0.0003 nan 0.1000 -0.0000
## 100 0.0001 nan 0.1000 -0.0000
## 120 0.0001 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold27: shrinkage=0.10, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold27: shrinkage=0.10, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0403 nan 0.1000 0.0030
## 2 0.0364 nan 0.1000 0.0000
## 3 0.0312 nan 0.1000 0.0033
## 4 0.0292 nan 0.1000 0.0006
## 5 0.0252 nan 0.1000 0.0034
## 6 0.0225 nan 0.1000 0.0022
## 7 0.0200 nan 0.1000 0.0025
## 8 0.0179 nan 0.1000 0.0017
## 9 0.0169 nan 0.1000 0.0010
## 10 0.0155 nan 0.1000 0.0010
## 20 0.0064 nan 0.1000 0.0006
## 40 0.0018 nan 0.1000 0.0001
## 60 0.0006 nan 0.1000 0.0000
## 80 0.0003 nan 0.1000 -0.0000
## 100 0.0001 nan 0.1000 -0.0000
## 120 0.0001 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold27: shrinkage=0.10, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold27: shrinkage=0.10, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0411 nan 0.1000 0.0016
## 2 0.0346 nan 0.1000 0.0053
## 3 0.0306 nan 0.1000 0.0010
## 4 0.0273 nan 0.1000 0.0018
## 5 0.0234 nan 0.1000 0.0031
## 6 0.0213 nan 0.1000 0.0022
## 7 0.0192 nan 0.1000 0.0006
## 8 0.0180 nan 0.1000 0.0011
## 9 0.0158 nan 0.1000 0.0016
## 10 0.0142 nan 0.1000 0.0017
## 20 0.0066 nan 0.1000 0.0003
## 40 0.0021 nan 0.1000 -0.0001
## 60 0.0011 nan 0.1000 0.0000
## 80 0.0006 nan 0.1000 0.0000
## 100 0.0003 nan 0.1000 -0.0000
## 120 0.0002 nan 0.1000 -0.0000
## 140 0.0001 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold27: shrinkage=0.10, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold27: shrinkage=0.10, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0393 nan 0.1000 -0.0000
## 2 0.0325 nan 0.1000 0.0071
## 3 0.0272 nan 0.1000 0.0046
## 4 0.0228 nan 0.1000 0.0031
## 5 0.0199 nan 0.1000 0.0013
## 6 0.0176 nan 0.1000 0.0025
## 7 0.0144 nan 0.1000 0.0018
## 8 0.0122 nan 0.1000 0.0012
## 9 0.0100 nan 0.1000 0.0014
## 10 0.0089 nan 0.1000 0.0007
## 20 0.0026 nan 0.1000 0.0002
## 40 0.0006 nan 0.1000 0.0000
## 60 0.0001 nan 0.1000 -0.0000
## 80 0.0000 nan 0.1000 0.0000
## 100 0.0000 nan 0.1000 0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 0.0000
##
## - Fold27: shrinkage=0.10, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold27: shrinkage=0.10, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0383 nan 0.1000 0.0057
## 2 0.0330 nan 0.1000 0.0045
## 3 0.0288 nan 0.1000 0.0045
## 4 0.0263 nan 0.1000 0.0011
## 5 0.0226 nan 0.1000 0.0023
## 6 0.0205 nan 0.1000 0.0003
## 7 0.0187 nan 0.1000 0.0010
## 8 0.0161 nan 0.1000 0.0006
## 9 0.0148 nan 0.1000 0.0015
## 10 0.0141 nan 0.1000 0.0006
## 20 0.0045 nan 0.1000 0.0003
## 40 0.0013 nan 0.1000 -0.0000
## 60 0.0005 nan 0.1000 -0.0000
## 80 0.0003 nan 0.1000 0.0000
## 100 0.0001 nan 0.1000 -0.0000
## 120 0.0001 nan 0.1000 0.0000
## 140 0.0000 nan 0.1000 0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 0.0000
##
## - Fold27: shrinkage=0.10, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold27: shrinkage=0.10, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0387 nan 0.1000 0.0061
## 2 0.0353 nan 0.1000 0.0031
## 3 0.0318 nan 0.1000 0.0025
## 4 0.0280 nan 0.1000 0.0038
## 5 0.0243 nan 0.1000 0.0026
## 6 0.0211 nan 0.1000 0.0018
## 7 0.0194 nan 0.1000 0.0012
## 8 0.0178 nan 0.1000 0.0007
## 9 0.0160 nan 0.1000 0.0017
## 10 0.0156 nan 0.1000 -0.0005
## 20 0.0084 nan 0.1000 0.0003
## 40 0.0035 nan 0.1000 -0.0003
## 60 0.0016 nan 0.1000 0.0000
## 80 0.0009 nan 0.1000 -0.0000
## 100 0.0005 nan 0.1000 0.0000
## 120 0.0003 nan 0.1000 -0.0000
## 140 0.0002 nan 0.1000 -0.0000
## 160 0.0001 nan 0.1000 -0.0000
## 180 0.0001 nan 0.1000 -0.0000
## 200 0.0001 nan 0.1000 -0.0000
##
## - Fold27: shrinkage=0.10, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold27: shrinkage=0.10, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0396 nan 0.1000 0.0021
## 2 0.0331 nan 0.1000 0.0035
## 3 0.0280 nan 0.1000 0.0023
## 4 0.0237 nan 0.1000 0.0025
## 5 0.0205 nan 0.1000 0.0024
## 6 0.0173 nan 0.1000 0.0027
## 7 0.0146 nan 0.1000 0.0026
## 8 0.0124 nan 0.1000 0.0016
## 9 0.0109 nan 0.1000 0.0008
## 10 0.0096 nan 0.1000 0.0002
## 20 0.0029 nan 0.1000 0.0001
## 40 0.0006 nan 0.1000 -0.0000
## 60 0.0002 nan 0.1000 -0.0000
## 80 0.0000 nan 0.1000 0.0000
## 100 0.0000 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 0.0000
##
## - Fold27: shrinkage=0.10, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold27: shrinkage=0.10, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0390 nan 0.1000 0.0048
## 2 0.0353 nan 0.1000 0.0032
## 3 0.0310 nan 0.1000 0.0020
## 4 0.0263 nan 0.1000 0.0047
## 5 0.0220 nan 0.1000 0.0039
## 6 0.0196 nan 0.1000 0.0027
## 7 0.0176 nan 0.1000 0.0013
## 8 0.0158 nan 0.1000 0.0017
## 9 0.0141 nan 0.1000 0.0010
## 10 0.0128 nan 0.1000 0.0014
## 20 0.0046 nan 0.1000 -0.0007
## 40 0.0011 nan 0.1000 -0.0000
## 60 0.0004 nan 0.1000 -0.0000
## 80 0.0002 nan 0.1000 -0.0000
## 100 0.0001 nan 0.1000 -0.0000
## 120 0.0001 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold27: shrinkage=0.10, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold27: shrinkage=0.10, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0385 nan 0.1000 0.0056
## 2 0.0336 nan 0.1000 0.0019
## 3 0.0294 nan 0.1000 0.0040
## 4 0.0271 nan 0.1000 0.0006
## 5 0.0241 nan 0.1000 0.0033
## 6 0.0212 nan 0.1000 0.0028
## 7 0.0189 nan 0.1000 0.0011
## 8 0.0174 nan 0.1000 0.0005
## 9 0.0161 nan 0.1000 0.0005
## 10 0.0154 nan 0.1000 0.0009
## 20 0.0075 nan 0.1000 -0.0003
## 40 0.0030 nan 0.1000 -0.0001
## 60 0.0014 nan 0.1000 -0.0000
## 80 0.0008 nan 0.1000 -0.0000
## 100 0.0005 nan 0.1000 -0.0000
## 120 0.0003 nan 0.1000 -0.0000
## 140 0.0001 nan 0.1000 -0.0000
## 160 0.0001 nan 0.1000 -0.0000
## 180 0.0001 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold27: shrinkage=0.10, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold28: shrinkage=0.01, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0407 nan 0.0100 0.0003
## 2 0.0402 nan 0.0100 0.0005
## 3 0.0397 nan 0.0100 0.0006
## 4 0.0392 nan 0.0100 0.0003
## 5 0.0387 nan 0.0100 0.0005
## 6 0.0383 nan 0.0100 0.0006
## 7 0.0378 nan 0.0100 0.0005
## 8 0.0373 nan 0.0100 0.0001
## 9 0.0369 nan 0.0100 0.0004
## 10 0.0365 nan 0.0100 0.0002
## 20 0.0324 nan 0.0100 0.0004
## 40 0.0269 nan 0.0100 0.0005
## 60 0.0219 nan 0.0100 0.0001
## 80 0.0180 nan 0.0100 0.0000
## 100 0.0149 nan 0.0100 0.0002
## 120 0.0121 nan 0.0100 0.0001
## 140 0.0101 nan 0.0100 0.0001
## 160 0.0083 nan 0.0100 -0.0000
## 180 0.0070 nan 0.0100 0.0001
## 200 0.0058 nan 0.0100 0.0000
##
## - Fold28: shrinkage=0.01, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold28: shrinkage=0.01, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0405 nan 0.0100 0.0005
## 2 0.0401 nan 0.0100 0.0003
## 3 0.0395 nan 0.0100 0.0007
## 4 0.0390 nan 0.0100 0.0004
## 5 0.0387 nan 0.0100 0.0001
## 6 0.0382 nan 0.0100 0.0004
## 7 0.0378 nan 0.0100 0.0002
## 8 0.0374 nan 0.0100 0.0002
## 9 0.0370 nan 0.0100 0.0003
## 10 0.0366 nan 0.0100 0.0004
## 20 0.0330 nan 0.0100 0.0001
## 40 0.0264 nan 0.0100 0.0001
## 60 0.0214 nan 0.0100 0.0001
## 80 0.0178 nan 0.0100 0.0001
## 100 0.0146 nan 0.0100 0.0000
## 120 0.0121 nan 0.0100 0.0000
## 140 0.0102 nan 0.0100 0.0001
## 160 0.0089 nan 0.0100 -0.0001
## 180 0.0077 nan 0.0100 0.0001
## 200 0.0066 nan 0.0100 0.0000
##
## - Fold28: shrinkage=0.01, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold28: shrinkage=0.01, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0406 nan 0.0100 0.0005
## 2 0.0402 nan 0.0100 0.0002
## 3 0.0399 nan 0.0100 -0.0001
## 4 0.0394 nan 0.0100 0.0005
## 5 0.0389 nan 0.0100 0.0005
## 6 0.0384 nan 0.0100 0.0002
## 7 0.0381 nan 0.0100 0.0003
## 8 0.0375 nan 0.0100 0.0005
## 9 0.0370 nan 0.0100 0.0005
## 10 0.0366 nan 0.0100 0.0004
## 20 0.0327 nan 0.0100 0.0002
## 40 0.0266 nan 0.0100 0.0001
## 60 0.0221 nan 0.0100 0.0002
## 80 0.0183 nan 0.0100 0.0001
## 100 0.0156 nan 0.0100 0.0000
## 120 0.0137 nan 0.0100 0.0000
## 140 0.0121 nan 0.0100 -0.0000
## 160 0.0106 nan 0.0100 0.0000
## 180 0.0094 nan 0.0100 0.0000
## 200 0.0085 nan 0.0100 0.0000
##
## - Fold28: shrinkage=0.01, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold28: shrinkage=0.01, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0403 nan 0.0100 0.0006
## 2 0.0399 nan 0.0100 0.0000
## 3 0.0394 nan 0.0100 0.0006
## 4 0.0387 nan 0.0100 0.0009
## 5 0.0380 nan 0.0100 0.0005
## 6 0.0375 nan 0.0100 0.0002
## 7 0.0370 nan 0.0100 0.0003
## 8 0.0365 nan 0.0100 0.0004
## 9 0.0361 nan 0.0100 0.0005
## 10 0.0356 nan 0.0100 0.0004
## 20 0.0311 nan 0.0100 0.0002
## 40 0.0241 nan 0.0100 0.0003
## 60 0.0182 nan 0.0100 0.0001
## 80 0.0138 nan 0.0100 0.0002
## 100 0.0113 nan 0.0100 -0.0001
## 120 0.0089 nan 0.0100 0.0001
## 140 0.0074 nan 0.0100 0.0001
## 160 0.0060 nan 0.0100 0.0000
## 180 0.0049 nan 0.0100 0.0000
## 200 0.0040 nan 0.0100 0.0000
##
## - Fold28: shrinkage=0.01, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold28: shrinkage=0.01, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0405 nan 0.0100 0.0006
## 2 0.0399 nan 0.0100 0.0003
## 3 0.0393 nan 0.0100 0.0005
## 4 0.0389 nan 0.0100 0.0004
## 5 0.0385 nan 0.0100 0.0003
## 6 0.0379 nan 0.0100 0.0006
## 7 0.0374 nan 0.0100 0.0003
## 8 0.0367 nan 0.0100 0.0005
## 9 0.0363 nan 0.0100 0.0001
## 10 0.0357 nan 0.0100 0.0005
## 20 0.0320 nan 0.0100 0.0003
## 40 0.0244 nan 0.0100 0.0003
## 60 0.0193 nan 0.0100 0.0002
## 80 0.0152 nan 0.0100 0.0001
## 100 0.0124 nan 0.0100 0.0000
## 120 0.0100 nan 0.0100 0.0001
## 140 0.0081 nan 0.0100 0.0001
## 160 0.0067 nan 0.0100 0.0000
## 180 0.0055 nan 0.0100 -0.0000
## 200 0.0046 nan 0.0100 0.0000
##
## - Fold28: shrinkage=0.01, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold28: shrinkage=0.01, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0406 nan 0.0100 0.0002
## 2 0.0400 nan 0.0100 0.0005
## 3 0.0395 nan 0.0100 0.0003
## 4 0.0390 nan 0.0100 0.0003
## 5 0.0386 nan 0.0100 0.0005
## 6 0.0382 nan 0.0100 0.0003
## 7 0.0379 nan 0.0100 0.0001
## 8 0.0374 nan 0.0100 0.0002
## 9 0.0369 nan 0.0100 0.0005
## 10 0.0365 nan 0.0100 0.0002
## 20 0.0332 nan 0.0100 0.0003
## 40 0.0271 nan 0.0100 0.0001
## 60 0.0224 nan 0.0100 0.0001
## 80 0.0188 nan 0.0100 0.0001
## 100 0.0162 nan 0.0100 0.0001
## 120 0.0140 nan 0.0100 0.0000
## 140 0.0122 nan 0.0100 0.0000
## 160 0.0106 nan 0.0100 -0.0001
## 180 0.0094 nan 0.0100 0.0000
## 200 0.0086 nan 0.0100 -0.0000
##
## - Fold28: shrinkage=0.01, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold28: shrinkage=0.01, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0406 nan 0.0100 0.0001
## 2 0.0399 nan 0.0100 0.0006
## 3 0.0396 nan 0.0100 -0.0000
## 4 0.0389 nan 0.0100 0.0005
## 5 0.0383 nan 0.0100 0.0004
## 6 0.0378 nan 0.0100 0.0004
## 7 0.0373 nan 0.0100 0.0003
## 8 0.0369 nan 0.0100 0.0000
## 9 0.0363 nan 0.0100 0.0002
## 10 0.0358 nan 0.0100 0.0005
## 20 0.0311 nan 0.0100 0.0002
## 40 0.0236 nan 0.0100 0.0004
## 60 0.0179 nan 0.0100 0.0002
## 80 0.0134 nan 0.0100 0.0001
## 100 0.0105 nan 0.0100 0.0002
## 120 0.0080 nan 0.0100 0.0000
## 140 0.0063 nan 0.0100 -0.0000
## 160 0.0050 nan 0.0100 -0.0000
## 180 0.0040 nan 0.0100 0.0000
## 200 0.0031 nan 0.0100 -0.0000
##
## - Fold28: shrinkage=0.01, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold28: shrinkage=0.01, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0403 nan 0.0100 0.0005
## 2 0.0397 nan 0.0100 0.0006
## 3 0.0394 nan 0.0100 0.0002
## 4 0.0387 nan 0.0100 0.0007
## 5 0.0381 nan 0.0100 0.0004
## 6 0.0376 nan 0.0100 0.0004
## 7 0.0371 nan 0.0100 0.0005
## 8 0.0365 nan 0.0100 0.0005
## 9 0.0361 nan 0.0100 -0.0001
## 10 0.0356 nan 0.0100 0.0005
## 20 0.0310 nan 0.0100 0.0002
## 40 0.0239 nan 0.0100 0.0003
## 60 0.0188 nan 0.0100 0.0001
## 80 0.0149 nan 0.0100 0.0001
## 100 0.0117 nan 0.0100 0.0001
## 120 0.0095 nan 0.0100 0.0001
## 140 0.0079 nan 0.0100 0.0001
## 160 0.0062 nan 0.0100 0.0001
## 180 0.0050 nan 0.0100 -0.0000
## 200 0.0041 nan 0.0100 -0.0000
##
## - Fold28: shrinkage=0.01, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold28: shrinkage=0.01, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0405 nan 0.0100 0.0005
## 2 0.0400 nan 0.0100 0.0006
## 3 0.0396 nan 0.0100 0.0004
## 4 0.0390 nan 0.0100 0.0005
## 5 0.0384 nan 0.0100 0.0005
## 6 0.0379 nan 0.0100 0.0004
## 7 0.0375 nan 0.0100 0.0001
## 8 0.0370 nan 0.0100 0.0004
## 9 0.0367 nan 0.0100 0.0002
## 10 0.0363 nan 0.0100 0.0002
## 20 0.0326 nan 0.0100 0.0002
## 40 0.0262 nan 0.0100 0.0003
## 60 0.0216 nan 0.0100 -0.0002
## 80 0.0182 nan 0.0100 0.0001
## 100 0.0152 nan 0.0100 0.0001
## 120 0.0134 nan 0.0100 0.0001
## 140 0.0118 nan 0.0100 0.0000
## 160 0.0103 nan 0.0100 0.0001
## 180 0.0094 nan 0.0100 -0.0000
## 200 0.0085 nan 0.0100 -0.0000
##
## - Fold28: shrinkage=0.01, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold28: shrinkage=0.05, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0381 nan 0.0500 0.0020
## 2 0.0372 nan 0.0500 -0.0003
## 3 0.0348 nan 0.0500 0.0020
## 4 0.0337 nan 0.0500 0.0000
## 5 0.0323 nan 0.0500 0.0016
## 6 0.0305 nan 0.0500 0.0018
## 7 0.0292 nan 0.0500 0.0012
## 8 0.0274 nan 0.0500 0.0011
## 9 0.0260 nan 0.0500 0.0015
## 10 0.0245 nan 0.0500 0.0013
## 20 0.0158 nan 0.0500 0.0004
## 40 0.0068 nan 0.0500 0.0003
## 60 0.0028 nan 0.0500 -0.0000
## 80 0.0013 nan 0.0500 -0.0000
## 100 0.0008 nan 0.0500 -0.0000
## 120 0.0004 nan 0.0500 -0.0000
## 140 0.0003 nan 0.0500 0.0000
## 160 0.0002 nan 0.0500 -0.0000
## 180 0.0001 nan 0.0500 0.0000
## 200 0.0001 nan 0.0500 -0.0000
##
## - Fold28: shrinkage=0.05, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold28: shrinkage=0.05, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0388 nan 0.0500 0.0025
## 2 0.0361 nan 0.0500 0.0017
## 3 0.0340 nan 0.0500 0.0021
## 4 0.0330 nan 0.0500 0.0005
## 5 0.0307 nan 0.0500 0.0009
## 6 0.0289 nan 0.0500 0.0015
## 7 0.0275 nan 0.0500 0.0014
## 8 0.0262 nan 0.0500 0.0010
## 9 0.0252 nan 0.0500 0.0008
## 10 0.0233 nan 0.0500 0.0016
## 20 0.0142 nan 0.0500 0.0002
## 40 0.0062 nan 0.0500 0.0000
## 60 0.0036 nan 0.0500 -0.0001
## 80 0.0020 nan 0.0500 0.0000
## 100 0.0012 nan 0.0500 0.0000
## 120 0.0008 nan 0.0500 0.0000
## 140 0.0005 nan 0.0500 0.0000
## 160 0.0003 nan 0.0500 -0.0000
## 180 0.0002 nan 0.0500 -0.0000
## 200 0.0001 nan 0.0500 -0.0000
##
## - Fold28: shrinkage=0.05, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold28: shrinkage=0.05, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0396 nan 0.0500 0.0018
## 2 0.0363 nan 0.0500 0.0023
## 3 0.0346 nan 0.0500 0.0013
## 4 0.0323 nan 0.0500 0.0017
## 5 0.0305 nan 0.0500 0.0015
## 6 0.0294 nan 0.0500 0.0004
## 7 0.0274 nan 0.0500 0.0014
## 8 0.0262 nan 0.0500 0.0013
## 9 0.0253 nan 0.0500 0.0012
## 10 0.0239 nan 0.0500 0.0014
## 20 0.0157 nan 0.0500 0.0005
## 40 0.0089 nan 0.0500 -0.0001
## 60 0.0055 nan 0.0500 0.0000
## 80 0.0034 nan 0.0500 -0.0000
## 100 0.0022 nan 0.0500 0.0001
## 120 0.0017 nan 0.0500 -0.0000
## 140 0.0012 nan 0.0500 0.0000
## 160 0.0009 nan 0.0500 -0.0000
## 180 0.0007 nan 0.0500 0.0000
## 200 0.0005 nan 0.0500 -0.0000
##
## - Fold28: shrinkage=0.05, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold28: shrinkage=0.05, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0381 nan 0.0500 0.0013
## 2 0.0353 nan 0.0500 0.0019
## 3 0.0341 nan 0.0500 0.0009
## 4 0.0323 nan 0.0500 0.0022
## 5 0.0302 nan 0.0500 0.0018
## 6 0.0275 nan 0.0500 0.0027
## 7 0.0256 nan 0.0500 0.0011
## 8 0.0245 nan 0.0500 0.0011
## 9 0.0228 nan 0.0500 0.0016
## 10 0.0214 nan 0.0500 0.0007
## 20 0.0112 nan 0.0500 -0.0002
## 40 0.0037 nan 0.0500 0.0001
## 60 0.0015 nan 0.0500 0.0000
## 80 0.0007 nan 0.0500 -0.0000
## 100 0.0003 nan 0.0500 0.0000
## 120 0.0002 nan 0.0500 -0.0000
## 140 0.0001 nan 0.0500 -0.0000
## 160 0.0000 nan 0.0500 -0.0000
## 180 0.0000 nan 0.0500 -0.0000
## 200 0.0000 nan 0.0500 -0.0000
##
## - Fold28: shrinkage=0.05, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold28: shrinkage=0.05, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0380 nan 0.0500 0.0018
## 2 0.0347 nan 0.0500 0.0014
## 3 0.0323 nan 0.0500 0.0015
## 4 0.0297 nan 0.0500 0.0011
## 5 0.0276 nan 0.0500 0.0019
## 6 0.0261 nan 0.0500 0.0009
## 7 0.0244 nan 0.0500 0.0017
## 8 0.0228 nan 0.0500 0.0016
## 9 0.0211 nan 0.0500 0.0002
## 10 0.0205 nan 0.0500 0.0003
## 20 0.0115 nan 0.0500 0.0004
## 40 0.0044 nan 0.0500 0.0001
## 60 0.0022 nan 0.0500 0.0000
## 80 0.0015 nan 0.0500 -0.0000
## 100 0.0010 nan 0.0500 -0.0000
## 120 0.0006 nan 0.0500 0.0000
## 140 0.0005 nan 0.0500 -0.0000
## 160 0.0003 nan 0.0500 -0.0000
## 180 0.0002 nan 0.0500 0.0000
## 200 0.0001 nan 0.0500 0.0000
##
## - Fold28: shrinkage=0.05, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold28: shrinkage=0.05, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0392 nan 0.0500 0.0011
## 2 0.0376 nan 0.0500 0.0015
## 3 0.0363 nan 0.0500 0.0004
## 4 0.0343 nan 0.0500 0.0008
## 5 0.0323 nan 0.0500 0.0018
## 6 0.0305 nan 0.0500 0.0015
## 7 0.0289 nan 0.0500 0.0017
## 8 0.0279 nan 0.0500 0.0008
## 9 0.0265 nan 0.0500 0.0014
## 10 0.0255 nan 0.0500 0.0007
## 20 0.0174 nan 0.0500 0.0009
## 40 0.0092 nan 0.0500 0.0001
## 60 0.0057 nan 0.0500 -0.0001
## 80 0.0041 nan 0.0500 -0.0000
## 100 0.0029 nan 0.0500 -0.0000
## 120 0.0021 nan 0.0500 -0.0001
## 140 0.0016 nan 0.0500 -0.0000
## 160 0.0012 nan 0.0500 -0.0000
## 180 0.0010 nan 0.0500 -0.0000
## 200 0.0007 nan 0.0500 -0.0000
##
## - Fold28: shrinkage=0.05, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold28: shrinkage=0.05, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0369 nan 0.0500 0.0028
## 2 0.0347 nan 0.0500 0.0011
## 3 0.0324 nan 0.0500 0.0020
## 4 0.0304 nan 0.0500 0.0007
## 5 0.0284 nan 0.0500 0.0015
## 6 0.0265 nan 0.0500 0.0010
## 7 0.0247 nan 0.0500 0.0012
## 8 0.0222 nan 0.0500 0.0013
## 9 0.0218 nan 0.0500 -0.0003
## 10 0.0200 nan 0.0500 0.0012
## 20 0.0101 nan 0.0500 0.0005
## 40 0.0037 nan 0.0500 -0.0002
## 60 0.0013 nan 0.0500 -0.0000
## 80 0.0006 nan 0.0500 -0.0000
## 100 0.0003 nan 0.0500 0.0000
## 120 0.0001 nan 0.0500 0.0000
## 140 0.0001 nan 0.0500 -0.0000
## 160 0.0000 nan 0.0500 -0.0000
## 180 0.0000 nan 0.0500 -0.0000
## 200 0.0000 nan 0.0500 0.0000
##
## - Fold28: shrinkage=0.05, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold28: shrinkage=0.05, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0385 nan 0.0500 0.0021
## 2 0.0358 nan 0.0500 0.0020
## 3 0.0334 nan 0.0500 0.0013
## 4 0.0304 nan 0.0500 0.0029
## 5 0.0290 nan 0.0500 0.0010
## 6 0.0274 nan 0.0500 0.0013
## 7 0.0258 nan 0.0500 0.0010
## 8 0.0234 nan 0.0500 0.0011
## 9 0.0220 nan 0.0500 0.0010
## 10 0.0214 nan 0.0500 0.0003
## 20 0.0117 nan 0.0500 0.0002
## 40 0.0042 nan 0.0500 0.0001
## 60 0.0019 nan 0.0500 -0.0000
## 80 0.0009 nan 0.0500 -0.0000
## 100 0.0006 nan 0.0500 -0.0000
## 120 0.0003 nan 0.0500 0.0000
## 140 0.0002 nan 0.0500 0.0000
## 160 0.0001 nan 0.0500 -0.0000
## 180 0.0001 nan 0.0500 -0.0000
## 200 0.0001 nan 0.0500 0.0000
##
## - Fold28: shrinkage=0.05, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold28: shrinkage=0.05, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0398 nan 0.0500 0.0001
## 2 0.0377 nan 0.0500 0.0010
## 3 0.0352 nan 0.0500 0.0020
## 4 0.0331 nan 0.0500 0.0011
## 5 0.0308 nan 0.0500 0.0019
## 6 0.0293 nan 0.0500 0.0016
## 7 0.0278 nan 0.0500 0.0014
## 8 0.0268 nan 0.0500 -0.0004
## 9 0.0248 nan 0.0500 0.0003
## 10 0.0236 nan 0.0500 0.0008
## 20 0.0154 nan 0.0500 0.0003
## 40 0.0090 nan 0.0500 0.0001
## 60 0.0060 nan 0.0500 0.0000
## 80 0.0040 nan 0.0500 -0.0001
## 100 0.0029 nan 0.0500 -0.0000
## 120 0.0021 nan 0.0500 -0.0001
## 140 0.0016 nan 0.0500 -0.0000
## 160 0.0011 nan 0.0500 0.0000
## 180 0.0009 nan 0.0500 -0.0000
## 200 0.0008 nan 0.0500 0.0000
##
## - Fold28: shrinkage=0.05, interaction.depth=3, n.minobsinnode=5, n.trees=200
## + Fold28: shrinkage=0.10, interaction.depth=1, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0349 nan 0.1000 0.0051
## 2 0.0317 nan 0.1000 0.0014
## 3 0.0298 nan 0.1000 -0.0017
## 4 0.0256 nan 0.1000 0.0024
## 5 0.0226 nan 0.1000 0.0033
## 6 0.0191 nan 0.1000 0.0024
## 7 0.0182 nan 0.1000 0.0003
## 8 0.0177 nan 0.1000 -0.0007
## 9 0.0153 nan 0.1000 0.0010
## 10 0.0146 nan 0.1000 -0.0003
## 20 0.0063 nan 0.1000 0.0006
## 40 0.0020 nan 0.1000 -0.0000
## 60 0.0008 nan 0.1000 -0.0000
## 80 0.0003 nan 0.1000 -0.0000
## 100 0.0001 nan 0.1000 -0.0000
## 120 0.0001 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold28: shrinkage=0.10, interaction.depth=1, n.minobsinnode=1, n.trees=200
## + Fold28: shrinkage=0.10, interaction.depth=1, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0359 nan 0.1000 0.0053
## 2 0.0301 nan 0.1000 0.0042
## 3 0.0265 nan 0.1000 0.0024
## 4 0.0240 nan 0.1000 0.0028
## 5 0.0203 nan 0.1000 0.0033
## 6 0.0192 nan 0.1000 0.0013
## 7 0.0168 nan 0.1000 0.0003
## 8 0.0151 nan 0.1000 0.0011
## 9 0.0146 nan 0.1000 -0.0000
## 10 0.0133 nan 0.1000 0.0009
## 20 0.0058 nan 0.1000 -0.0001
## 40 0.0016 nan 0.1000 0.0000
## 60 0.0006 nan 0.1000 0.0000
## 80 0.0003 nan 0.1000 -0.0000
## 100 0.0001 nan 0.1000 -0.0000
## 120 0.0001 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold28: shrinkage=0.10, interaction.depth=1, n.minobsinnode=3, n.trees=200
## + Fold28: shrinkage=0.10, interaction.depth=1, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0397 nan 0.1000 -0.0025
## 2 0.0342 nan 0.1000 0.0049
## 3 0.0306 nan 0.1000 0.0033
## 4 0.0285 nan 0.1000 0.0020
## 5 0.0259 nan 0.1000 0.0025
## 6 0.0235 nan 0.1000 0.0023
## 7 0.0222 nan 0.1000 0.0008
## 8 0.0205 nan 0.1000 0.0014
## 9 0.0192 nan 0.1000 0.0003
## 10 0.0178 nan 0.1000 0.0008
## 20 0.0094 nan 0.1000 0.0004
## 40 0.0047 nan 0.1000 0.0002
## 60 0.0025 nan 0.1000 -0.0001
## 80 0.0015 nan 0.1000 -0.0000
## 100 0.0007 nan 0.1000 -0.0000
## 120 0.0004 nan 0.1000 -0.0000
## 140 0.0003 nan 0.1000 0.0000
## 160 0.0002 nan 0.1000 -0.0000
## 180 0.0001 nan 0.1000 -0.0000
## 200 0.0001 nan 0.1000 0.0000
##
## - Fold28: shrinkage=0.10, interaction.depth=1, n.minobsinnode=5, n.trees=200
## + Fold28: shrinkage=0.10, interaction.depth=2, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0377 nan 0.1000 0.0007
## 2 0.0328 nan 0.1000 0.0037
## 3 0.0291 nan 0.1000 -0.0007
## 4 0.0252 nan 0.1000 0.0032
## 5 0.0217 nan 0.1000 0.0024
## 6 0.0186 nan 0.1000 0.0016
## 7 0.0172 nan 0.1000 0.0002
## 8 0.0171 nan 0.1000 -0.0014
## 9 0.0154 nan 0.1000 0.0015
## 10 0.0142 nan 0.1000 0.0009
## 20 0.0040 nan 0.1000 0.0005
## 40 0.0008 nan 0.1000 -0.0000
## 60 0.0002 nan 0.1000 -0.0000
## 80 0.0001 nan 0.1000 -0.0000
## 100 0.0000 nan 0.1000 0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold28: shrinkage=0.10, interaction.depth=2, n.minobsinnode=1, n.trees=200
## + Fold28: shrinkage=0.10, interaction.depth=2, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0358 nan 0.1000 0.0057
## 2 0.0332 nan 0.1000 0.0015
## 3 0.0299 nan 0.1000 0.0032
## 4 0.0257 nan 0.1000 0.0034
## 5 0.0248 nan 0.1000 -0.0006
## 6 0.0228 nan 0.1000 0.0002
## 7 0.0223 nan 0.1000 -0.0011
## 8 0.0208 nan 0.1000 0.0009
## 9 0.0197 nan 0.1000 0.0015
## 10 0.0181 nan 0.1000 0.0003
## 20 0.0063 nan 0.1000 -0.0004
## 40 0.0014 nan 0.1000 -0.0000
## 60 0.0006 nan 0.1000 0.0000
## 80 0.0002 nan 0.1000 -0.0000
## 100 0.0001 nan 0.1000 0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold28: shrinkage=0.10, interaction.depth=2, n.minobsinnode=3, n.trees=200
## + Fold28: shrinkage=0.10, interaction.depth=2, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0379 nan 0.1000 0.0014
## 2 0.0336 nan 0.1000 0.0045
## 3 0.0291 nan 0.1000 0.0039
## 4 0.0272 nan 0.1000 0.0004
## 5 0.0246 nan 0.1000 0.0027
## 6 0.0235 nan 0.1000 0.0003
## 7 0.0216 nan 0.1000 0.0010
## 8 0.0205 nan 0.1000 0.0010
## 9 0.0186 nan 0.1000 0.0019
## 10 0.0176 nan 0.1000 -0.0005
## 20 0.0098 nan 0.1000 0.0001
## 40 0.0043 nan 0.1000 -0.0002
## 60 0.0022 nan 0.1000 -0.0001
## 80 0.0011 nan 0.1000 -0.0000
## 100 0.0006 nan 0.1000 -0.0000
## 120 0.0003 nan 0.1000 -0.0000
## 140 0.0002 nan 0.1000 -0.0000
## 160 0.0002 nan 0.1000 -0.0000
## 180 0.0001 nan 0.1000 -0.0000
## 200 0.0001 nan 0.1000 0.0000
##
## - Fold28: shrinkage=0.10, interaction.depth=2, n.minobsinnode=5, n.trees=200
## + Fold28: shrinkage=0.10, interaction.depth=3, n.minobsinnode=1, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0372 nan 0.1000 0.0038
## 2 0.0330 nan 0.1000 0.0040
## 3 0.0272 nan 0.1000 0.0030
## 4 0.0242 nan 0.1000 0.0011
## 5 0.0217 nan 0.1000 0.0030
## 6 0.0185 nan 0.1000 0.0029
## 7 0.0157 nan 0.1000 0.0011
## 8 0.0150 nan 0.1000 -0.0002
## 9 0.0125 nan 0.1000 0.0012
## 10 0.0120 nan 0.1000 0.0002
## 20 0.0036 nan 0.1000 -0.0005
## 40 0.0007 nan 0.1000 0.0000
## 60 0.0001 nan 0.1000 -0.0000
## 80 0.0000 nan 0.1000 -0.0000
## 100 0.0000 nan 0.1000 -0.0000
## 120 0.0000 nan 0.1000 -0.0000
## 140 0.0000 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold28: shrinkage=0.10, interaction.depth=3, n.minobsinnode=1, n.trees=200
## + Fold28: shrinkage=0.10, interaction.depth=3, n.minobsinnode=3, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0354 nan 0.1000 0.0036
## 2 0.0323 nan 0.1000 0.0030
## 3 0.0271 nan 0.1000 0.0043
## 4 0.0240 nan 0.1000 0.0032
## 5 0.0222 nan 0.1000 0.0017
## 6 0.0207 nan 0.1000 0.0014
## 7 0.0189 nan 0.1000 0.0015
## 8 0.0155 nan 0.1000 0.0011
## 9 0.0142 nan 0.1000 0.0007
## 10 0.0122 nan 0.1000 0.0014
## 20 0.0050 nan 0.1000 0.0000
## 40 0.0017 nan 0.1000 -0.0001
## 60 0.0006 nan 0.1000 -0.0000
## 80 0.0003 nan 0.1000 -0.0000
## 100 0.0002 nan 0.1000 0.0000
## 120 0.0001 nan 0.1000 -0.0000
## 140 0.0001 nan 0.1000 -0.0000
## 160 0.0000 nan 0.1000 -0.0000
## 180 0.0000 nan 0.1000 -0.0000
## 200 0.0000 nan 0.1000 -0.0000
##
## - Fold28: shrinkage=0.10, interaction.depth=3, n.minobsinnode=3, n.trees=200
## + Fold28: shrinkage=0.10, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0350 nan 0.1000 0.0048
## 2 0.0328 nan 0.1000 0.0007
## 3 0.0307 nan 0.1000 0.0004
## 4 0.0269 nan 0.1000 0.0035
## 5 0.0248 nan 0.1000 0.0016
## 6 0.0227 nan 0.1000 0.0015
## 7 0.0202 nan 0.1000 0.0018
## 8 0.0193 nan 0.1000 0.0005
## 9 0.0184 nan 0.1000 0.0005
## 10 0.0172 nan 0.1000 0.0007
## 20 0.0085 nan 0.1000 0.0000
## 40 0.0040 nan 0.1000 -0.0000
## 60 0.0018 nan 0.1000 -0.0000
## 80 0.0012 nan 0.1000 -0.0001
## 100 0.0008 nan 0.1000 -0.0000
## 120 0.0005 nan 0.1000 -0.0000
## 140 0.0003 nan 0.1000 -0.0000
## 160 0.0002 nan 0.1000 -0.0000
## 180 0.0001 nan 0.1000 -0.0000
## 200 0.0001 nan 0.1000 0.0000
##
## - Fold28: shrinkage=0.10, interaction.depth=3, n.minobsinnode=5, n.trees=200
## Aggregating results
## Selecting tuning parameters
## Fitting n.trees = 200, interaction.depth = 1, shrinkage = 0.05, n.minobsinnode = 1 on full training set
## Iter TrainDeviance ValidDeviance StepSize Improve
## 1 0.0403 nan 0.0500 0.0023
## 2 0.0378 nan 0.0500 0.0028
## 3 0.0362 nan 0.0500 0.0014
## 4 0.0334 nan 0.0500 0.0024
## 5 0.0328 nan 0.0500 -0.0006
## 6 0.0311 nan 0.0500 0.0010
## 7 0.0295 nan 0.0500 0.0014
## 8 0.0275 nan 0.0500 0.0021
## 9 0.0261 nan 0.0500 0.0005
## 10 0.0248 nan 0.0500 0.0013
## 20 0.0145 nan 0.0500 0.0006
## 40 0.0061 nan 0.0500 0.0002
## 60 0.0032 nan 0.0500 0.0000
## 80 0.0017 nan 0.0500 -0.0000
## 100 0.0009 nan 0.0500 -0.0000
## 120 0.0005 nan 0.0500 -0.0000
## 140 0.0003 nan 0.0500 0.0000
## 160 0.0002 nan 0.0500 0.0000
## 180 0.0001 nan 0.0500 0.0000
## 200 0.0001 nan 0.0500 0.0000Brad’s theory notes
Leaving this section here, it is to be deleted as we incorporate what we need from here into the explanatory model part
Running a different logistic model for each country
We now have a table to test some glmer modelling on.
Following this tutorial Marga sent and applying to the test data:
https://raffaelevacca.github.io/Intro-multilevel-with-R/
Testing a nested dataset by country
# Commented the below as we are probably not gonna use it
#
# nested.cntry <- complete_df %>%
# group_by(country) %>%
# nest()
#
# # The column nested.df$data is a list of data frames, one for each country
# class(nested.cntry$data) # type, list
# length(nested.cntry$data) # number of countries
#
# # to unnest()
# nested.cntry %>%
# filter(country == "AT") %>%
# dplyr::select(country, data) %>%
# unnest(cols = c(data))
# # Using the nested data, we now run a model for each country:
# # fit separate lm for each each element of nested.cntry$data)
# lmodels <- nested.cntry %>%
# # Get all data frames
# pull(data) %>%
# # Run glm() on each via map because it's a classification model
# # model run against all vairables for now.
# purrr::map(~ glm(trans_docs ~ .,
# data= .x,
# family = "binomial"))
#
# # show that it's a list and we can call each elements regression output.
# class(lmodels)
# lmodels[4]Mixed models
Fixed effects: Things that are the same across the cluster Random effects: Things that change within the cluster
The fixed and random effects could refer to either the intercept or the slope, as these can both vary between groups.
LMM equation structure in R
To run a multilevel linear model, we use the lmer() function (“Linear Mixed Effects in R”) from the lme4 package. The syntax is similar to regression. everything to the left of the | indicates the effects that should be random, and the variable to the right of the | is the grouping variable across which the effects should vary
Null model This has no slope, but random intercepts. It basically just takes the average. It has no independent (X) variables and is the proper naïve model.
null_model <- lmer(Y ~ (1|cntry), data = ess)
Random intercept model: –> Only the intercept differ. The slopes are equal for each group. We assume the same effect of X on Y for each group. Just that the group causes the difference.
random_int_model <- lmer(Y ~ X + (1 | group), data=df)
Random intercept, random slope model –> Now we also let the slope vary by group. This means each group basically has it’s own model. It is
random_intslope_model <- lmer(Y ~ X + (X | group), data=df)
For each, Y=target, X = independent vars (can be many)
Standard LMM Modelling Strategy
(sourced from slides here: https://favstats.github.io/intro_multilevel/slides/#54) ^ This is a useful resource, it goes through an ESS modelling doc
Approach to multilevel model building based on Hox (2010)
1/ Null Model (Random Intercept only) 2/ Add independent Level 1 variables 3/ Add independent Level 2 variables 4/ Add random slopes 5/ (Cross-level) interactions
Each step, check whether your model is significantly improved compared to the previous one.
Basic LMM testing with toy data
First, null model:
# m_null <- glmer(trans_docs ~ (1|country),
# data = complete_df,
# family = "binomial",
# control = glmerControl(optimizer = "bobyqa"),
# nAGQ = 10)
# summary(m_null)To come back and reinterpret… don’t really know at this stage.
Test flexplot and broom.mixed usage:
# #devtools::install_github("dustinfife/flexplot")
# library(flexplot)Here it has some examples of code and output for saved logistic model fits
# # don't think flexplot will be super useful as we have so many categorical variables
# flexplot::logistic_fit
# flexplot::mixed_logistic
# flexplot::visualize(m_null)
#
# # broom.mixed is used to tidy up the stats outputs into a tibble
# broom.mixed::tidy(m_null) # summary output in tibble
# broom.mixed::glance(m_null) # model performance summaryRandom effects model
- Including individual level variables only with country:
# n_randeffect <- glmer(trans_docs ~
# gender + age + I(age^2) + life_sat + religion + social_class +
# (1|country),
# data = complete_df,
# family = "binomial",
# control = glmerControl(optimizer = "bobyqa"),
# nAGQ = 10)This suggests the data needs to be rescaled, to check which variables are the issue:
# # check for nearzero variance, if so those could be removed
# nearZeroVar(complete_df, saveMetrics = TRUE)
# # see no issues. So all variables stay.
#
# # will recode the numeric variables I selected, which is only age
# scaled_df <- complete_df |>
# mutate(across(where(is.numeric), scale))Re check the random effects model with scaled data:
# n_randeffect <- glmer(trans_docs ~
# gender + age + I(age^2) + life_sat + (1|country),
# data = scaled_df,
# family = "binomial",
# control = glmerControl(optimizer = "bobyqa"),
# nAGQ = 10)
#
#
#
# summary(n_randeffect)Can we interpret this…
Example Random effects models: m <- glmer(remission ~ IL6 + CRP + CancerStage + LengthofStay + Experience + (1 | DID), data = hdp, family = binomial, control = glmerControl(optimizer = “bobyqa”), nAGQ = 10)
Example from last year code glm_model_4 <- glmer(binary_qc19 ~ male + d11 + I(d11^2) + political_ideology + Religion_cat + sd1_7_factor + d60_ordinal + qc15_1_ordinal + prop_gndr_bin + prop_dis_wide + Unemployment + (1 | country_name), data = Data, family = binomial, control = glmerControl(optimizer = “bobyqa”, optCtrl = list(maxfun = 100000)))
Potentially useful package for visualising and interpreting linear mixed models: Flexplot -> https://github.com/dustinfife/flexplot Functions to quickly visualise LMM models and compare their performance.
broom.mixed The function broom.mixed::tidy() gives us all model parameters (random and fixed).
Useful calculations: - ICC (intra cluster correlation. How alike each of the observations within each group are) - ANOVA for model comparison: anova(null_model, lvl1_preds_model, lvl2_preds_model, rs_preds_model)
Social class
Although D63 of the questionnaire measures (oneself’s and one’s household’s) self-perceived social class, it is still a relevant and seemingly divisive variable. We observe a positive correlation, where support grows with increasing (perceived) social class, while explicit lack of support and no response are higher for lower-class individuals.